id stringlengths 2 115 | lastModified stringlengths 24 24 | tags list | author stringlengths 2 42 ⌀ | description stringlengths 0 6.67k ⌀ | citation stringlengths 0 10.7k ⌀ | likes int64 0 3.66k | downloads int64 0 8.89M | created timestamp[us] | card stringlengths 11 977k | card_len int64 11 977k | embeddings list |
|---|---|---|---|---|---|---|---|---|---|---|---|
yuvalkirstain/task_prediction_test | 2023-10-31T06:18:46.000Z | [
"region:us"
] | yuvalkirstain | null | null | 0 | 12 | 2023-10-31T06:18:44 | ---
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
dataset_info:
features:
- name: task
dtype: string
- name: text
dtype: string
- name: path
dtype: string
splits:
- name: test
num_bytes: 381506
num_examples: 4168
download_size: 96504
dataset_size: 381506
---
# Dataset Card for "task_prediction_test"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 507 | [
[
-0.0301055908203125,
-0.0208892822265625,
0.01074981689453125,
0.01462554931640625,
-0.00036025047302246094,
-0.0108642578125,
0.01300048828125,
-0.01529693603515625,
0.04022216796875,
0.02691650390625,
-0.072021484375,
-0.040008544921875,
-0.04901123046875,
... |
Adi-0-0-Gupta/Tomato | 2023-10-31T08:02:45.000Z | [
"region:us"
] | Adi-0-0-Gupta | null | null | 0 | 12 | 2023-10-31T08:01:33 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: valid
path: data/valid-*
dataset_info:
features:
- name: image
struct:
- name: bytes
dtype: binary
- name: path
dtype: 'null'
- name: label
dtype: int64
splits:
- name: train
num_bytes: 813795751
num_examples: 8527
- name: valid
num_bytes: 20170032
num_examples: 208
download_size: 821987045
dataset_size: 833965783
---
# Dataset Card for "Tomato"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 645 | [
[
-0.04656982421875,
-0.0184478759765625,
0.023834228515625,
-0.0009007453918457031,
-0.0022792816162109375,
0.007411956787109375,
0.01454925537109375,
-0.017181396484375,
0.0753173828125,
0.033172607421875,
-0.056793212890625,
-0.053985595703125,
-0.0564575195312... |
Lollitor/MyPubChem2 | 2023-10-31T10:25:12.000Z | [
"region:us"
] | Lollitor | null | null | 0 | 12 | 2023-10-31T10:23:00 | ---
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 295081.2
num_examples: 1800
- name: validation
num_bytes: 32786.8
num_examples: 200
download_size: 103924
dataset_size: 327868.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---
# Dataset Card for "MyPubChem2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 555 | [
[
-0.042816162109375,
-0.01502227783203125,
0.0137176513671875,
0.024688720703125,
-0.01055145263671875,
-0.0023365020751953125,
0.0250701904296875,
-0.00820159912109375,
0.05401611328125,
0.0361328125,
-0.0545654296875,
-0.034820556640625,
-0.03509521484375,
... |
kosta-naumenko/medflex | 2023-11-02T16:32:52.000Z | [
"region:us"
] | kosta-naumenko | null | null | 0 | 12 | 2023-10-31T13:14:13 | ---
dataset_info:
features:
- name: tokens
sequence: string
- name: ner_tags
sequence: int64
splits:
- name: train
num_bytes: 1288027
num_examples: 394
download_size: 0
dataset_size: 1288027
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "medflex"
'tokens' - список списков слов предложений (is_split_into_words=True при токенизации)
'ner_tags' - список списков классов слов
- 0 - не симптом
- 1 - начало симптома
- 2 - продолжение симптома
Пример дальнейшей обработки - https://huggingface.co/learn/nlp-course/chapter7/2
| 620 | [
[
-0.0197296142578125,
-0.048187255859375,
0.00984954833984375,
0.00400543212890625,
-0.034423828125,
0.0202789306640625,
-0.002544403076171875,
-0.0017538070678710938,
0.04107666015625,
0.0253448486328125,
-0.06915283203125,
-0.057220458984375,
-0.0333251953125,
... |
mponty/code_tutorials | 2023-11-01T02:22:58.000Z | [
"task_categories:text-generation",
"size_categories:100K<n<1M",
"language:en",
"language:ru",
"language:zh",
"language:es",
"code",
"region:us"
] | mponty | null | null | 1 | 12 | 2023-10-31T14:32:09 | ---
dataset_info:
features:
- name: text
dtype: string
- name: url
dtype: string
- name: dump
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 3124929718.313386
num_examples: 518410
download_size: 2971113091
dataset_size: 3124929718.313386
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
task_categories:
- text-generation
language:
- en
- ru
- zh
- es
tags:
- code
pretty_name: k
size_categories:
- 100K<n<1M
---
# Coding Tutorials
This comprehensive dataset consists of **500,000** documents, summing up to around **1.5 billion** tokens.
Predominantly composed of coding tutorials, it has been meticulously compiled from various web crawl datasets like **RefinedWeb**, **OSCAR**, and **Escorpius**.
The selection process involved a stringent filtering of files using regular expressions to ensure the inclusion of content that contains programming code (most of them).
These tutorials offer more than mere code snippets.
They provide an extensive context, including the rationale behind the code, the problem being addressed, and detailed step-by-step instructions.
This layered context is helpful for training a code-LM model, enabling it to discern the user intent behind a piece of code and thus facilitating more contextually relevant assistance.
### Programming Language Distribution
```
cpp ▏ 39% █████████████████████████
python ▏ 25% ████████████████
java ▏ 16% ██████████
csharp ▏ 3% ██
javascript ▏ 1% ▋
kotlin ▏ 1% ▋
other ▏ 14% █████████
```
### Natural language distribution
```
en ▏ 80% █████████████████████████
ru ▏ 16% █████
zh ▏ 2% ▋
es ▏ 2% ▋
``` | 1,771 | [
[
-0.02789306640625,
-0.040130615234375,
0.019775390625,
0.0173492431640625,
-0.00862884521484375,
0.0182342529296875,
-0.0130767822265625,
-0.006526947021484375,
0.0036067962646484375,
0.03460693359375,
-0.04388427734375,
-0.06927490234375,
-0.021240234375,
0... |
derekiya/bigquery | 2023-10-31T20:48:59.000Z | [
"region:us"
] | derekiya | null | null | 0 | 12 | 2023-10-31T20:38:25 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
zhaospei/cmg-history | 2023-11-01T11:53:00.000Z | [
"region:us"
] | zhaospei | null | null | 0 | 12 | 2023-11-01T11:52:25 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Dnsibu/serial2023 | 2023-11-02T21:23:22.000Z | [
"region:us"
] | Dnsibu | null | null | 0 | 12 | 2023-11-01T22:55:59 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: 'Sentence #'
dtype: string
- name: Word
dtype: string
- name: POS
dtype: string
- name: Tag
dtype:
class_label:
names:
'0': O
'1': B-serial
splits:
- name: train
num_bytes: 24256517
num_examples: 836762
- name: test
num_bytes: 6076775
num_examples: 209191
download_size: 6868292
dataset_size: 30333292
---
# Dataset Card for "serial2023"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 716 | [
[
-0.04034423828125,
-0.008453369140625,
0.0197906494140625,
0.031524658203125,
-0.023895263671875,
0.015960693359375,
0.03521728515625,
-0.007076263427734375,
0.059112548828125,
0.0300445556640625,
-0.058013916015625,
-0.03790283203125,
-0.0382080078125,
-0.0... |
Zaid/CGSQuAD | 2023-11-02T06:42:11.000Z | [
"region:us"
] | Zaid | null | null | 0 | 12 | 2023-11-02T06:42:09 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: title
dtype: string
- name: context
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: answer_start
dtype: int64
- name: is_impossible
dtype: bool
- name: count
dtype: int64
- name: ID
dtype: string
- name: answers
struct:
- name: answer_start
sequence: int64
- name: text
sequence: string
splits:
- name: train
num_bytes: 14944089
num_examples: 1504
download_size: 106212
dataset_size: 14944089
---
# Dataset Card for "CGSQuAD"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 806 | [
[
-0.041748046875,
-0.0308837890625,
0.0128173828125,
0.0156402587890625,
-0.023223876953125,
0.003917694091796875,
0.0106201171875,
-0.01450347900390625,
0.0511474609375,
0.0240478515625,
-0.049224853515625,
-0.05810546875,
-0.045501708984375,
-0.033081054687... |
lvwerra/codeparrot-valid | 2021-08-10T14:18:44.000Z | [
"region:us"
] | lvwerra | null | null | 0 | 11 | 2022-03-02T23:29:22 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
masked-neuron/amazon | 2021-11-28T05:42:27.000Z | [
"region:us"
] | masked-neuron | null | 0 | 11 | 2022-03-02T23:29:22 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... | |
microsoft/codexglue_method_generation | 2021-10-28T07:03:55.000Z | [
"region:us"
] | microsoft | null | null | 7 | 11 | 2022-03-02T23:29:22 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
mrm8488/fake-news | 2021-10-15T16:06:35.000Z | [
"region:us"
] | mrm8488 | null | null | 0 | 11 | 2022-03-02T23:29:22 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
sarulab-speech/bvcc-voicemos2022 | 2022-02-25T06:26:53.000Z | [
"region:us"
] | sarulab-speech | This dataset is for internal use only. For voicemos challenge | @misc{cooper2021generalization,
title={Generalization Ability of MOS Prediction Networks},
author={Erica Cooper and Wen-Chin Huang and Tomoki Toda and Junichi Yamagishi},
year={2021},
eprint={2110.02635},
archivePrefix={arXiv},
primaryClass={eess.AS}
} | 0 | 11 | 2022-03-02T23:29:22 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
wanyu/IteraTeR_human_doc | 2022-10-24T18:58:15.000Z | [
"task_categories:text2text-generation",
"annotations_creators:crowdsourced",
"language_creators:found",
"multilinguality:monolingual",
"source_datasets:original",
"language:en",
"license:apache-2.0",
"conditional-text-generation",
"text-editing",
"arxiv:2203.03802",
"region:us"
] | wanyu | null | null | 1 | 11 | 2022-03-13T20:48:31 | ---
annotations_creators:
- crowdsourced
language_creators:
- found
language:
- en
license:
- apache-2.0
multilinguality:
- monolingual
source_datasets:
- original
task_categories:
- text2text-generation
task_ids: []
pretty_name: IteraTeR-human-doc
language_bcp47:
- en-US
tags:
- conditional-text-generation
- text-editing
---
Paper: [Understanding Iterative Revision from Human-Written Text](https://arxiv.org/abs/2203.03802)
Authors: Wanyu Du, Vipul Raheja, Dhruv Kumar, Zae Myung Kim, Melissa Lopez, Dongyeop Kang
Github repo: https://github.com/vipulraheja/IteraTeR
| 575 | [
[
-0.00531768798828125,
-0.03533935546875,
0.05169677734375,
0.00943756103515625,
-0.0235748291015625,
0.0160980224609375,
-0.018524169921875,
-0.0180816650390625,
0.0008001327514648438,
0.05657958984375,
-0.046051025390625,
-0.0289306640625,
-0.0164947509765625,
... |
huggan/CelebA-faces-with-attributes | 2022-04-01T08:27:55.000Z | [
"region:us"
] | huggan | null | null | 2 | 11 | 2022-03-31T15:01:15 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
chainyo/rvl-cdip | 2022-04-06T16:49:20.000Z | [
"license:other",
"region:us"
] | chainyo | null | null | 2 | 11 | 2022-04-06T07:06:56 | ---
license: other
---
The RVL-CDIP (Ryerson Vision Lab Complex Document Information Processing) dataset consists of 400,000 grayscale images in 16 classes, with 25,000 images per class. There are 320,000 training images, 40,000 validation images, and 40,000 test images. The images are sized so their largest dimension does not exceed 1000 pixels.
For questions and comments please contact Adam Harley (aharley@scs.ryerson.ca).
The full dataset can be found [here](https://www.cs.cmu.edu/~aharley/rvl-cdip/).
## Labels
0: advertissement
1: budget
2: email
3: file folder
4: form
5: handwritten
6: invoice
7: letter
8: memo
9: news article
10: presentation
11: questionnaire
12: resume
13: scientific publication
14: scientific report
15: specification
## Citation
This dataset is from this [paper](https://www.cs.cmu.edu/~aharley/icdar15/) `A. W. Harley, A. Ufkes, K. G. Derpanis, "Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval," in ICDAR, 2015`
## License
RVL-CDIP is a subset of IIT-CDIP, which came from the [Legacy Tobacco Document Library](https://www.industrydocuments.ucsf.edu/tobacco/), for which license information can be found [here](https://www.industrydocuments.ucsf.edu/help/copyright/).
## References
1. D. Lewis, G. Agam, S. Argamon, O. Frieder, D. Grossman, and J. Heard, "Building a test collection for complex document information processing," in Proc. 29th Annual Int. ACM SIGIR Conference (SIGIR 2006), pp. 665-666, 2006
2. The Legacy Tobacco Document Library (LTDL), University of California, San Francisco, 2007. http://legacy.library.ucsf.edu/.
| 1,719 | [
[
-0.034454345703125,
-0.0263671875,
0.041748046875,
0.0049896240234375,
0.003238677978515625,
0.007411956787109375,
-0.01227569580078125,
-0.03424072265625,
-0.034881591796875,
0.04534912109375,
-0.020599365234375,
-0.055694580078125,
-0.054412841796875,
0.00... |
surafelkindu/Amharic_corpus | 2022-04-17T18:19:47.000Z | [
"license:mit",
"region:us"
] | surafelkindu | null | null | 1 | 11 | 2022-04-17T18:06:43 | ---
license: mit
---
ዛጎል ዜና- መንግስት አምስት ሺህ የሚጠጉ እስረኞችን “ተመራቂዎች” በሚል መፍታቱን ይፋ ባደረገበት ቀን በተመሳሳይ አምቦ ተማሪዎች ተቃውሞ ማሰማታቸው ተሰማ። ተማሪዎቹ የአስቸኳይ አዋጁን በመጣስ ” መረራ ይፈታ” እያሉ ተቃውሞ መጀመራቸው ነው የተሰማው። ከትምህርት ቤት ወደ ትምህርት ቤት የሰፋው ተቃውሞ ብህይወት ላይ አደጋ ባያስከትልም በንብረት ላይ ግን ጉዳት አድርሷል። መኪና ሲቃጠል ያዩ የአይን ምስክሮች ተቃውሞውን በጀመሩት ላይም ሆነ ዘግይተው በተቀላቀሉት ላይ እንደ ቀደሞው ያለ የሃይል እርምጃ አልተወሰደም። የኦሮሚያ ሚዲያ ኔት ወርክ እንዳለው ደግሞ በርካታ ሰዎች ታስረዋል።
ለወትሮው ህገ መንግስቱን በሃይል ለመናድ የተነሱ፣ የነውጥ ሃይሎች፣ አተራማሾች፣ የጥፋት ሃይል ተላላኪዎች በሚል ተጠርጥረው በቁጥጥር ስር ከዋሉት መካከል 4035 የሚሆኑት ሲፈቱ እስረኞቹ “ስድስት ኮርስ ወስደው ተመረቁ” ነው የተባለው።
የኦሮሚያ ማረሚያ ቤቶች አስተዳደር ኮሚሽነር ፀሃይ በላይን ጠቅሶ ፋና እንደዘገበው ጦላይ ተሃድሶ ማዕከል ከገቡ 5 ሺህ 600 ሰልጣኞች መካከል 4035 ያህሉ በስድስት ዋና ዋና ጉዳዮች ሥልጠና ወስደው ተመርቀዋል። ኮርሶቹም በፍፁም፣ አይደገምም፣ የቀለም አብዮት፣ የኢትዮጰያ ህገ–መንግስት እና የኢትዮጵያ ህዳሴ የሚሉ ርዕሰ ጉዳዮችን የተካተቱባቸው ነው።
አበምርቃቱ ላይ ጠቅላይ ሚኒስትር ሃይለማርያም ተገኝተው “ ሽኝት” አደርጉላቸው ተብሏል። በርካታ ቃል ተገብቶላቸዋል። መስመርም ተሰምሮላቸዋል። “በደምና በአጥንት የተጻፈውን ሕገመንግስት፣ ዋጋ የተከፈለበትን ህገመንግስት” በማለት አቶ ሃይለማርያም በሃይል ለመናድ መሞከር አይቻልም በለዋል። “ ልክ እናንተ አይደገምም እንዳላችሁት፣ እኛም አይደገም እንላለን” ብለዋል። የፋና ዘገባ እንዲህ ይነበባል።
አዲስ አበባ ፣ ታህሳስ 12 ፣ 2009 (ኤፍ ቢ ሲ) በሃገሪቱ የተለያዩ አካባቢዎች በተፈጠረው ሁከት ውስጥ ተሳትፈው በማሰልጠኛ ጣቢያዎች የተሃድሶ ስልጠና ሲወስዱ የነበሩ ዜጎች ወደ መጡበት እየተመለሱ ነው። በአዋሽ፣ አላጌና ብር ሸለቆ ማዕከላት የተሃድሶ ስልጠና የወሰዱ ዜጎች ናቸው ወደ አካባቢያቸው እየተመለሱ ያሉት። በጦላይ ለአንድ ወር የተሃድሶ ስልጠና የወሰዱ 4 ሺህ 35 ዜጎችም ሥልጠናቸውን አጠናቀው ነገ ወደ መጡበት አካባቢ ይመለሳሉ ተብሏል።
በጦላይ የተሃድሶ ማዕከል የተገኙት ጠቅላይ ሚኒስትር ኃይለማርያም ደሳለኝ በዚሁ ጊዜ ባስተላለፉት መልዕክት ሰልጣኞች ወደ መደበኛ ህይወታቸው እንዲመለሱ መንግሥት ድጋፍ ያደርጋል ብለዋል። ሠራተኞች ወደ ሥራ ገበታቸው እንዲመለሱ የሚደረግ ሲሆን ተማሪዎች ደግሞ ትምህርታቸው እንዲቀጥሉ ይደረጋልም ነው ያሉት ጠቅላይ ሚኒስትር ኃይለማርያም።
ሥራ አጥ የሆኑ ወጣቶችም በራሳቸው መንገድ ሥራ እንዲፈጥሩ ድጋፍ እንደሚደረግላቸው ጠቅላይ ሚኒስትሩ ገልጸዋል። ሠላም፣ ልማትና ዴሞክራሲ የማይነጣጡ የአንድ አገር ህልውና መሰረት መሆናቸውን ወጣቱ ተገንዝቦ እነዚህን እሴቶች የመጠበቅ ኃላፊነቱን እንዲወጣ ጠይቀዋል። ወጣቱ ጥያቄ እንኳ ቢኖረው ሕገ-መንግሥቱ በሚፈቅደው መሰረት የማቅረብና መልስ የማግኘት መብት እንዳለው ገልጸዋል። ባለፉት ወራት እንደታየው ጥያቄውን በአመጽና ግርግር መጠየቁ ዋጋ እንዳስከፈለ ለማሳያነት በማንሳት።
እንዲህ ዓይነት ሁኔታ እንዳይደገም መንግሥትም የራሱን ስህተት ለማረም ጥልቅ ተሃድሶ እያደረገ መሆኑን ገልጸው ወጣቱም የራሱን ስህተት በማረም ከመንግሥት ጋር በመሆን ሠላሙን እንዲጠብቅ መልዕክት አስተላልፈዋል። የኦሮሚያ ክልል ርዕሰ መስተዳደር አቶ ለማ መገርሳ በበኩላቸው በክልሉ የሰፈነውን ሠላም ለማስቀጠል ከሁሉም የህብረተሰብ ክፍል ጋር በቅንጅት ሥራዎች ይሰራሉ ብለዋል።
ከወራት በፊት በተፈጠረው ሁከትና ግርግር ህይወት የጠፋ መሆኑን ገልጸው ለዘመናት የተለፋባቸው የህዝብ ኃብቶችም መውደማቸው አግባብ አለመሆኑን ተናግረዋል። ክልሉ ሊለወጥና ሊለማ የሚችለው የክልሉ ወጣቶች ለሠላም በጋራ ዘብ ሲቆሙ እንደሆነም አስምረውበታል።
አሁን ወደ | 2,214 | [
[
-0.03851318359375,
-0.023345947265625,
0.0006556510925292969,
0.0400390625,
-0.036590576171875,
-0.041839599609375,
0.01119232177734375,
-0.015167236328125,
0.016021728515625,
0.055938720703125,
0.004199981689453125,
-0.0253448486328125,
-0.034698486328125,
... |
strombergnlp/twitter_pos | 2022-10-25T21:43:15.000Z | [
"task_categories:token-classification",
"task_ids:part-of-speech",
"annotations_creators:expert-generated",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"source_datasets:original",
"language:en",
"license:cc-by-4.0",
"region:us"
] | strombergnlp | Part-of-speech information is basic NLP task. However, Twitter text
is difficult to part-of-speech tag: it is noisy, with linguistic errors and idiosyncratic style.
This dataset contains two datasets for English PoS tagging for tweets:
* Ritter, with train/dev/test
* Foster, with dev/test
Splits defined in the Derczynski paper, but the data is from Ritter and Foster.
For more details see:
* https://gate.ac.uk/wiki/twitter-postagger.html
* https://aclanthology.org/D11-1141.pdf
* https://www.aaai.org/ocs/index.php/ws/aaaiw11/paper/download/3912/4191 | @inproceedings{ritter2011named,
title={Named entity recognition in tweets: an experimental study},
author={Ritter, Alan and Clark, Sam and Etzioni, Oren and others},
booktitle={Proceedings of the 2011 conference on empirical methods in natural language processing},
pages={1524--1534},
year={2011}
}
@inproceedings{foster2011hardtoparse,
title={\# hardtoparse: POS Tagging and Parsing the Twitterverse},
author={Foster, Jennifer and Cetinoglu, Ozlem and Wagner, Joachim and Le Roux, Joseph and Hogan, Stephen and Nivre, Joakim and Hogan, Deirdre and Van Genabith, Josef},
booktitle={Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence},
year={2011}
}
@inproceedings{derczynski2013twitter,
title={Twitter part-of-speech tagging for all: Overcoming sparse and noisy data},
author={Derczynski, Leon and Ritter, Alan and Clark, Sam and Bontcheva, Kalina},
booktitle={Proceedings of the international conference recent advances in natural language processing ranlp 2013},
pages={198--206},
year={2013}
} | 2 | 11 | 2022-05-06T19:09:49 | ---
annotations_creators:
- expert-generated
language_creators:
- found
language:
- en
license:
- cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- token-classification
task_ids:
- part-of-speech
paperswithcode_id: ritter-pos
pretty_name: Twitter Part-of-speech
---
# Dataset Card for "twitter-pos"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://gate.ac.uk/wiki/twitter-postagger.html](https://gate.ac.uk/wiki/twitter-postagger.html)
- **Repository:** [https://github.com/GateNLP/gateplugin-Twitter](https://github.com/GateNLP/gateplugin-Twitter)
- **Paper:** [https://aclanthology.org/R13-1026/](https://aclanthology.org/R13-1026/)
- **Point of Contact:** [Leon Derczynski](https://github.com/leondz)
- **Size of downloaded dataset files:** 51.96 MiB
- **Size of the generated dataset:** 251.22 KiB
- **Total amount of disk used:** 52.05 MB
### Dataset Summary
Part-of-speech information is basic NLP task. However, Twitter text
is difficult to part-of-speech tag: it is noisy, with linguistic errors and idiosyncratic style.
This dataset contains two datasets for English PoS tagging for tweets:
* Ritter, with train/dev/test
* Foster, with dev/test
Splits defined in the Derczynski paper, but the data is from Ritter and Foster.
* Ritter: [https://aclanthology.org/D11-1141.pdf](https://aclanthology.org/D11-1141.pdf),
* Foster: [https://www.aaai.org/ocs/index.php/ws/aaaiw11/paper/download/3912/4191](https://www.aaai.org/ocs/index.php/ws/aaaiw11/paper/download/3912/4191)
### Supported Tasks and Leaderboards
* [Part of speech tagging on Ritter](https://paperswithcode.com/sota/part-of-speech-tagging-on-ritter)
### Languages
English, non-region-specific. `bcp47:en`
## Dataset Structure
### Data Instances
An example of 'train' looks as follows.
```
{'id': '0', 'tokens': ['Antick', 'Musings', 'post', ':', 'Book-A-Day', '2010', '#', '243', '(', '10/4', ')', '--', 'Gray', 'Horses', 'by', 'Hope', 'Larson', 'http://bit.ly/as8fvc'], 'pos_tags': [23, 23, 22, 9, 23, 12, 22, 12, 5, 12, 6, 9, 23, 23, 16, 23, 23, 51]}
```
### Data Fields
The data fields are the same among all splits.
#### twitter-pos
- `id`: a `string` feature.
- `tokens`: a `list` of `string` features.
- `pos_tags`: a `list` of classification labels (`int`). Full tagset with indices:
```python
```
### Data Splits
| name |tokens|sentences|
|---------|----:|---------:|
|ritter train|10652|551|
|ritter dev |2242|118|
|ritter test |2291|118|
|foster dev |2998|270|
|foster test |2841|250|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
### Citation Information
```
@inproceedings{ritter2011named,
title={Named entity recognition in tweets: an experimental study},
author={Ritter, Alan and Clark, Sam and Etzioni, Oren and others},
booktitle={Proceedings of the 2011 conference on empirical methods in natural language processing},
pages={1524--1534},
year={2011}
}
@inproceedings{foster2011hardtoparse,
title={\# hardtoparse: POS Tagging and Parsing the Twitterverse},
author={Foster, Jennifer and Cetinoglu, Ozlem and Wagner, Joachim and Le Roux, Joseph and Hogan, Stephen and Nivre, Joakim and Hogan, Deirdre and Van Genabith, Josef},
booktitle={Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence},
year={2011}
}
@inproceedings{derczynski2013twitter,
title={Twitter part-of-speech tagging for all: Overcoming sparse and noisy data},
author={Derczynski, Leon and Ritter, Alan and Clark, Sam and Bontcheva, Kalina},
booktitle={Proceedings of the international conference recent advances in natural language processing ranlp 2013},
pages={198--206},
year={2013}
}
```
### Contributions
Author uploaded ([@leondz](https://github.com/leondz)) | 6,592 | [
[
-0.0306549072265625,
-0.040008544921875,
0.0111083984375,
0.01995849609375,
-0.019866943359375,
0.01406097412109375,
-0.03076171875,
-0.0308685302734375,
0.0498046875,
0.0158233642578125,
-0.051025390625,
-0.0714111328125,
-0.045867919921875,
0.0044670104980... |
lmqg/qg_subjqa | 2022-12-02T18:56:32.000Z | [
"task_categories:text-generation",
"task_ids:language-modeling",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"source_datasets:subjqa",
"language:en",
"license:cc-by-4.0",
"question-generation",
"arxiv:2210.03992",
"region:us"
] | lmqg | [SubjQA](https://github.com/megagonlabs/SubjQA) dataset for question generation (QG) task. | @inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
} | 0 | 11 | 2022-05-11T11:16:13 | ---
license: cc-by-4.0
pretty_name: SubjQA for question generation
language: en
multilinguality: monolingual
size_categories: 10K<n<100K
source_datasets: subjqa
task_categories:
- text-generation
task_ids:
- language-modeling
tags:
- question-generation
---
# Dataset Card for "lmqg/qg_subjqa"
## Dataset Description
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
- **Point of Contact:** [Asahi Ushio](http://asahiushio.com/)
### Dataset Summary
This is a subset of [QG-Bench](https://github.com/asahi417/lm-question-generation/blob/master/QG_BENCH.md#datasets), a unified question generation benchmark proposed in
["Generative Language Models for Paragraph-Level Question Generation: A Unified Benchmark and Evaluation, EMNLP 2022 main conference"](https://arxiv.org/abs/2210.03992).
Modified version of [SubjQA](https://github.com/megagonlabs/SubjQA) for question generation (QG) task.
### Supported Tasks and Leaderboards
* `question-generation`: The dataset can be used to train a model for question generation.
Success on this task is typically measured by achieving a high BLEU4/METEOR/ROUGE-L/BERTScore/MoverScore (see our paper for more in detail).
### Languages
English (en)
## Dataset Structure
An example of 'train' looks as follows.
```
{
"question": "How is book?",
"paragraph": "I am giving "Gone Girl" 3 stars, but only begrudgingly. In my mind, any book that takes me 3 months and 20 different tries to read is not worth 3 stars, especially a book written by an author I already respect. And I am not kidding, for me the first half of "Gone Girl" was a PURE TORTURE to read.Amy Dunn disappears on the day of her 5th wedding anniversary. All gradually uncovered evidence suggests that her husband, Nick, is somehow involved. Did he kill her? Was she kidnapped? What happened to Amy? One thing is clear, Nick and Amy's marriage wasn't as perfect as everybody thought.The first part of the novel is all about the investigation into Amy's disappearance, slow unraveling of Nick's dirty secrets, reminiscing about the troubled history of Nick and Amy's marriage as told in Amy's hidden diary. I strained and strained my brain trying to understand why this chunk of Gone Girl had no appeal to me whatsoever. The only answer I have is this: I am really not into reading about rich white people's problems. You want to whine to me about your dwindling trust fund? Losing your cushy New York job? Moving south and "only" renting a mansion there? Being unhappy because you have too much free time on your hands and you are used to only work as a hobby? You want to make fun of your lowly, un-posh neighbors and their casseroles? Well, I am not interested. I'd rather read about someone not necessarily likable, but at least worthy of my empathy, not waste my time on self-centered, spoiled, pathetic people who don't know what real problems are. Granted, characters in Flynn's previous novels ("Sharp Objects" and "Dark Places") are pretty pathetic and and at times revolting too, but I always felt some strange empathy towards them, not annoyance and boredom, like I felt reading about Amy and Nick's marriage voes.But then second part, with its wicked twist, changed everything. The story became much more exciting, dangerous and deranged. The main characters revealed sides to them that were quite shocking and VERY entertaining. I thought the Gillian Flynn I knew before finally unleashed her talent for writing utterly unlikable and crafty women. THEN I got invested in the story, THEN I cared.Was it too little too late though? I think it was. Something needed to be done to make "Gone Girl" a better read. Make it shorter? Cut out first part completely? I don't know. But because of my uneven experience with this novel I won't be able to recommend "Gone Girl" as readily as I did Flynn's earlier novels, even though I think this horror marriage story (it's not a true mystery, IMO) has some brilliantly written psycho goodness in it and an absolutely messed up ending that many loathed but I LOVED. I wish it didn't take so much time and patience to get to all of that...",
"answer": "any book that takes me 3 months and 20 different tries to read is not worth 3 stars",
"sentence": "In my mind, any book that takes me 3 months and 20 different tries to read is not worth 3 stars , especially a book written by an author I already respect.",
"paragraph_sentence": "I am giving "Gone Girl" 3 stars, but only begrudgingly. <hl> In my mind, any book that takes me 3 months and 20 different tries to read is not worth 3 stars , especially a book written by an author I already respect. <hl> And I am not kidding, for me the first half of "Gone Girl" was a PURE TORTURE to read. Amy Dunn disappears on the day of her 5th wedding anniversary. All gradually uncovered evidence suggests that her husband, Nick, is somehow involved. Did he kill her? Was she kidnapped? What happened to Amy? One thing is clear, Nick and Amy's marriage wasn't as perfect as everybody thought. The first part of the novel is all about the investigation into Amy's disappearance, slow unraveling of Nick's dirty secrets, reminiscing about the troubled history of Nick and Amy's marriage as told in Amy's hidden diary. I strained and strained my brain trying to understand why this chunk of Gone Girl had no appeal to me whatsoever. The only answer I have is this: I am really not into reading about rich white people's problems. You want to whine to me about your dwindling trust fund? Losing your cushy New York job? Moving south and "only" renting a mansion there? Being unhappy because you have too much free time on your hands and you are used to only work as a hobby? You want to make fun of your lowly, un-posh neighbors and their casseroles? Well, I am not interested. I'd rather read about someone not necessarily likable, but at least worthy of my empathy, not waste my time on self-centered, spoiled, pathetic people who don't know what real problems are. Granted, characters in Flynn's previous novels ("Sharp Objects" and "Dark Places") are pretty pathetic and and at times revolting too, but I always felt some strange empathy towards them, not annoyance and boredom, like I felt reading about Amy and Nick's marriage voes. But then second part, with its wicked twist, changed everything. The story became much more exciting, dangerous and deranged. The main characters revealed sides to them that were quite shocking and VERY entertaining. I thought the Gillian Flynn I knew before finally unleashed her talent for writing utterly unlikable and crafty women. THEN I got invested in the story, THEN I cared. Was it too little too late though? I think it was. Something needed to be done to make "Gone Girl" a better read. Make it shorter? Cut out first part completely? I don't know. But because of my uneven experience with this novel I won't be able to recommend "Gone Girl" as readily as I did Flynn's earlier novels, even though I think this horror marriage story (it's not a true mystery, IMO) has some brilliantly written psycho goodness in it and an absolutely messed up ending that many loathed but I LOVED. I wish it didn't take so much time and patience to get to all of that...",
"paragraph_answer": "I am giving "Gone Girl" 3 stars, but only begrudgingly. In my mind, <hl> any book that takes me 3 months and 20 different tries to read is not worth 3 stars <hl>, especially a book written by an author I already respect. And I am not kidding, for me the first half of "Gone Girl" was a PURE TORTURE to read.Amy Dunn disappears on the day of her 5th wedding anniversary. All gradually uncovered evidence suggests that her husband, Nick, is somehow involved. Did he kill her? Was she kidnapped? What happened to Amy? One thing is clear, Nick and Amy's marriage wasn't as perfect as everybody thought.The first part of the novel is all about the investigation into Amy's disappearance, slow unraveling of Nick's dirty secrets, reminiscing about the troubled history of Nick and Amy's marriage as told in Amy's hidden diary. I strained and strained my brain trying to understand why this chunk of Gone Girl had no appeal to me whatsoever. The only answer I have is this: I am really not into reading about rich white people's problems. You want to whine to me about your dwindling trust fund? Losing your cushy New York job? Moving south and "only" renting a mansion there? Being unhappy because you have too much free time on your hands and you are used to only work as a hobby? You want to make fun of your lowly, un-posh neighbors and their casseroles? Well, I am not interested. I'd rather read about someone not necessarily likable, but at least worthy of my empathy, not waste my time on self-centered, spoiled, pathetic people who don't know what real problems are. Granted, characters in Flynn's previous novels ("Sharp Objects" and "Dark Places") are pretty pathetic and and at times revolting too, but I always felt some strange empathy towards them, not annoyance and boredom, like I felt reading about Amy and Nick's marriage voes.But then second part, with its wicked twist, changed everything. The story became much more exciting, dangerous and deranged. The main characters revealed sides to them that were quite shocking and VERY entertaining. I thought the Gillian Flynn I knew before finally unleashed her talent for writing utterly unlikable and crafty women. THEN I got invested in the story, THEN I cared.Was it too little too late though? I think it was. Something needed to be done to make "Gone Girl" a better read. Make it shorter? Cut out first part completely? I don't know. But because of my uneven experience with this novel I won't be able to recommend "Gone Girl" as readily as I did Flynn's earlier novels, even though I think this horror marriage story (it's not a true mystery, IMO) has some brilliantly written psycho goodness in it and an absolutely messed up ending that many loathed but I LOVED. I wish it didn't take so much time and patience to get to all of that...",
"sentence_answer": "In my mind, <hl> any book that takes me 3 months and 20 different tries to read is not worth 3 stars <hl> , especially a book written by an author I already respect.",
"paragraph_id": "1b7cc3db9ec681edd253a41a2785b5a9",
"question_subj_level": 1,
"answer_subj_level": 1,
"domain": "books"
}
```
The data fields are the same among all splits.
- `question`: a `string` feature.
- `paragraph`: a `string` feature.
- `answer`: a `string` feature.
- `sentence`: a `string` feature.
- `paragraph_answer`: a `string` feature, which is same as the paragraph but the answer is highlighted by a special token `<hl>`.
- `paragraph_sentence`: a `string` feature, which is same as the paragraph but a sentence containing the answer is highlighted by a special token `<hl>`.
- `sentence_answer`: a `string` feature, which is same as the sentence but the answer is highlighted by a special token `<hl>`.
Each of `paragraph_answer`, `paragraph_sentence`, and `sentence_answer` feature is assumed to be used to train a question generation model,
but with different information. The `paragraph_answer` and `sentence_answer` features are for answer-aware question generation and
`paragraph_sentence` feature is for sentence-aware question generation.
### Data Splits
| name |train|validation|test |
|-------------|----:|---------:|----:|
|default (all)|4437 | 659 |1489 |
| books |636 | 91 |190 |
| electronics |696 | 98 |237 |
| movies |723 | 100 |153 |
| grocery |686 | 100 |378 |
| restaurants |822 | 128 |135 |
| tripadvisor |874 | 142 |396 |
## Citation Information
```
@inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}
``` | 12,341 | [
[
-0.03729248046875,
-0.06463623046875,
0.0699462890625,
-0.0194549560546875,
-0.04278564453125,
-0.027618408203125,
0.0142974853515625,
-0.0167083740234375,
0.02008056640625,
0.03668212890625,
-0.05926513671875,
-0.0238037109375,
-0.0330810546875,
0.012817382... |
HuggingFaceM4/something_something_v2 | 2022-10-20T21:35:22.000Z | [
"task_categories:other",
"annotations_creators:crowdsourced",
"language_creators:crowdsourced",
"multilinguality:monolingual",
"size_categories:100K<n<1M",
"source_datasets:original",
"language:en",
"license:other",
"arxiv:1706.04261",
"region:us"
] | HuggingFaceM4 | The Something-Something dataset (version 2) is a collection of 220,847 labeled video clips of humans performing pre-defined, basic actions with everyday objects. It is designed to train machine learning models in fine-grained understanding of human hand gestures like putting something into something, turning something upside down and covering something with something. | @inproceedings{goyal2017something,
title={The" something something" video database for learning and evaluating visual common sense},
author={Goyal, Raghav and Ebrahimi Kahou, Samira and Michalski, Vincent and Materzynska, Joanna and Westphal, Susanne and Kim, Heuna and Haenel, Valentin and Fruend, Ingo and Yianilos, Peter and Mueller-Freitag, Moritz and others},
booktitle={Proceedings of the IEEE international conference on computer vision},
pages={5842--5850},
year={2017}
} | 2 | 11 | 2022-05-12T21:27:54 | ---
annotations_creators:
- crowdsourced
language_creators:
- crowdsourced
language:
- en
license:
- other
multilinguality:
- monolingual
size_categories:
- 100K<n<1M
source_datasets:
- original
task_categories:
- other
task_ids: []
paperswithcode_id: something-something
pretty_name: Something Something v2
tags: []
---
# Dataset Card for Something Something v2
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://developer.qualcomm.com/software/ai-datasets/something-something
- **Repository:**
- **Paper:** https://arxiv.org/abs/1706.04261
- **Leaderboard:** https://paperswithcode.com/sota/action-recognition-in-videos-on-something
- **Point of Contact:** mailto: research.datasets@qti.qualcomm.com
### Dataset Summary
The Something-Something dataset (version 2) is a collection of 220,847 labeled video clips of humans performing pre-defined, basic actions with everyday objects. It is designed to train machine learning models in fine-grained understanding of human hand gestures like putting something into something, turning something upside down and covering something with something.
### Supported Tasks and Leaderboards
- `action-recognition`: The goal of this task is to classify actions happening in a video. This is a multilabel classification. The leaderboard is available [here](https://paperswithcode.com/sota/action-recognition-in-videos-on-something)
### Languages
The annotations in the dataset are in English.
## Dataset Structure
### Data Instances
```
{
"video_id": "41775",
"video": "<ExFileObject name="">",
"text": "moving drawer of night stand",
"label": 33,
"placeholders": ["drawer", "night stand"]}
}
```
### Data Fields
- `video_id`: `str` Unique identifier for each video.
- `video`: `str` File object
- `placeholders`: `List[str]` Objects present in the video
- `text`: `str` Description of what is happening in the video
- `labels`: `int` Action found in the video. Indices from 0 to 173.
<details>
<summary>
Click here to see the full list of Something-Something-v2 class labels mapping:
</summary>
|0 | Approaching something with your camera |
|1 | Attaching something to something |
|2 | Bending something so that it deforms |
|3 | Bending something until it breaks |
|4 | Burying something in something |
|5 | Closing something |
|6 | Covering something with something |
|7 | Digging something out of something |
|8 | Dropping something behind something |
|9 | Dropping something in front of something |
|10 | Dropping something into something |
|11 | Dropping something next to something |
|12 | Dropping something onto something |
|13 | Failing to put something into something because something does not fit |
|14 | Folding something |
|15 | Hitting something with something |
|16 | Holding something |
|17 | Holding something behind something |
|18 | Holding something in front of something |
|19 | Holding something next to something |
|20 | Holding something over something |
|21 | Laying something on the table on its side, not upright |
|22 | Letting something roll along a flat surface |
|23 | Letting something roll down a slanted surface |
|24 | Letting something roll up a slanted surface, so it rolls back down |
|25 | Lifting a surface with something on it but not enough for it to slide down |
|26 | Lifting a surface with something on it until it starts sliding down |
|27 | Lifting something up completely without letting it drop down |
|28 | Lifting something up completely, then letting it drop down |
|29 | Lifting something with something on it |
|30 | Lifting up one end of something without letting it drop down |
|31 | Lifting up one end of something, then letting it drop down |
|32 | Moving away from something with your camera |
|33 | Moving part of something |
|34 | Moving something across a surface until it falls down |
|35 | Moving something across a surface without it falling down |
|36 | Moving something and something away from each other |
|37 | Moving something and something closer to each other |
|38 | Moving something and something so they collide with each other |
|39 | Moving something and something so they pass each other |
|40 | Moving something away from something |
|41 | Moving something away from the camera |
|42 | Moving something closer to something |
|43 | Moving something down |
|44 | Moving something towards the camera |
|45 | Moving something up |
|46 | Opening something |
|47 | Picking something up |
|48 | Piling something up |
|49 | Plugging something into something |
|50 | Plugging something into something but pulling it right out as you remove your hand |
|51 | Poking a hole into some substance |
|52 | Poking a hole into something soft |
|53 | Poking a stack of something so the stack collapses |
|54 | Poking a stack of something without the stack collapsing |
|55 | Poking something so it slightly moves |
|56 | Poking something so lightly that it doesn't or almost doesn't move |
|57 | Poking something so that it falls over |
|58 | Poking something so that it spins around |
|59 | Pouring something into something |
|60 | Pouring something into something until it overflows |
|61 | Pouring something onto something |
|62 | Pouring something out of something |
|63 | Pretending or failing to wipe something off of something |
|64 | Pretending or trying and failing to twist something |
|65 | Pretending to be tearing something that is not tearable |
|66 | Pretending to close something without actually closing it |
|67 | Pretending to open something without actually opening it |
|68 | Pretending to pick something up |
|69 | Pretending to poke something |
|70 | Pretending to pour something out of something, but something is empty |
|71 | Pretending to put something behind something |
|72 | Pretending to put something into something |
|73 | Pretending to put something next to something |
|74 | Pretending to put something on a surface |
|75 | Pretending to put something onto something |
|76 | Pretending to put something underneath something |
|77 | Pretending to scoop something up with something |
|78 | Pretending to spread air onto something |
|79 | Pretending to sprinkle air onto something |
|80 | Pretending to squeeze something |
|81 | Pretending to take something from somewhere |
|82 | Pretending to take something out of something |
|83 | Pretending to throw something |
|84 | Pretending to turn something upside down |
|85 | Pulling something from behind of something |
|86 | Pulling something from left to right |
|87 | Pulling something from right to left |
|88 | Pulling something onto something |
|89 | Pulling something out of something |
|90 | Pulling two ends of something but nothing happens |
|91 | Pulling two ends of something so that it gets stretched |
|92 | Pulling two ends of something so that it separates into two pieces |
|93 | Pushing something from left to right |
|94 | Pushing something from right to left |
|95 | Pushing something off of something |
|96 | Pushing something onto something |
|97 | Pushing something so it spins |
|98 | Pushing something so that it almost falls off but doesn't |
|99 | Pushing something so that it falls off the table |
|100 | Pushing something so that it slightly moves |
|101 | Pushing something with something |
|102 | Putting number of something onto something |
|103 | Putting something and something on the table |
|104 | Putting something behind something |
|105 | Putting something in front of something |
|106 | Putting something into something |
|107 | Putting something next to something |
|108 | Putting something on a flat surface without letting it roll |
|109 | Putting something on a surface |
|110 | Putting something on the edge of something so it is not supported and falls down |
|111 | Putting something onto a slanted surface but it doesn't glide down |
|112 | Putting something onto something |
|113 | Putting something onto something else that cannot support it so it falls down |
|114 | Putting something similar to other things that are already on the table |
|115 | Putting something that can't roll onto a slanted surface, so it slides down |
|116 | Putting something that can't roll onto a slanted surface, so it stays where it is |
|117 | Putting something that cannot actually stand upright upright on the table, so it falls on its side |
|118 | Putting something underneath something |
|119 | Putting something upright on the table |
|120 | Putting something, something and something on the table |
|121 | Removing something, revealing something behind |
|122 | Rolling something on a flat surface |
|123 | Scooping something up with something |
|124 | Showing a photo of something to the camera |
|125 | Showing something behind something |
|126 | Showing something next to something |
|127 | Showing something on top of something |
|128 | Showing something to the camera |
|129 | Showing that something is empty |
|130 | Showing that something is inside something |
|131 | Something being deflected from something |
|132 | Something colliding with something and both are being deflected |
|133 | Something colliding with something and both come to a halt |
|134 | Something falling like a feather or paper |
|135 | Something falling like a rock |
|136 | Spilling something behind something |
|137 | Spilling something next to something |
|138 | Spilling something onto something |
|139 | Spinning something so it continues spinning |
|140 | Spinning something that quickly stops spinning |
|141 | Spreading something onto something |
|142 | Sprinkling something onto something |
|143 | Squeezing something |
|144 | Stacking number of something |
|145 | Stuffing something into something |
|146 | Taking one of many similar things on the table |
|147 | Taking something from somewhere |
|148 | Taking something out of something |
|149 | Tearing something into two pieces |
|150 | Tearing something just a little bit |
|151 | Throwing something |
|152 | Throwing something against something |
|153 | Throwing something in the air and catching it |
|154 | Throwing something in the air and letting it fall |
|155 | Throwing something onto a surface |
|156 | Tilting something with something on it slightly so it doesn't fall down |
|157 | Tilting something with something on it until it falls off |
|158 | Tipping something over |
|159 | Tipping something with something in it over, so something in it falls out |
|160 | Touching (without moving) part of something |
|161 | Trying but failing to attach something to something because it doesn't stick |
|162 | Trying to bend something unbendable so nothing happens |
|163 | Trying to pour something into something, but missing so it spills next to it |
|164 | Turning something upside down |
|165 | Turning the camera downwards while filming something |
|166 | Turning the camera left while filming something |
|167 | Turning the camera right while filming something |
|168 | Turning the camera upwards while filming something |
|169 | Twisting (wringing) something wet until water comes out |
|170 | Twisting something |
|171 | Uncovering something |
|172 | Unfolding something |
|173 | Wiping something off of something |
</details>
### Data Splits
| |train |validation| test |
|-------------|------:|---------:|------:|
|# of examples|168913|24777 |27157 |
## Dataset Creation
### Curation Rationale
From the paper:
> Neural networks trained on datasets such as ImageNet have led to major advances
in visual object classification. One obstacle that prevents networks from reasoning more
deeply about complex scenes and situations, and from integrating visual knowledge with natural language,
like humans do, is their lack of common sense knowledge about the physical world.
Videos, unlike still images, contain a wealth of detailed information about the physical world.
However, most labelled video datasets represent high-level concepts rather than detailed physical aspects
about actions and scenes. In this work, we describe our ongoing collection of the
“something-something” database of video prediction tasks whose solutions require a common sense
understanding of the depicted situation
### Source Data
#### Initial Data Collection and Normalization
From the paper:
> As outlined is Section 3 videos available online are largely unsuitable for the goal of learning
simple (but finegrained) visual concepts. We therefore ask crowd-workers to provide videos
given labels instead of the other way around.
#### Who are the source language producers?
The dataset authors
### Annotations
#### Annotation process
The label is given first and then the video is collected by an AMT worker. More fine-grained details on the process are in the Section 4 of the work.
#### Who are the annotators?
AMT workers
### Personal and Sensitive Information
Nothing specifically discussed in the paper.
## Considerations for Using the Data
### Social Impact of Dataset
The dataset is useful for action recognition pretraining due to diverse set of actions that happen in it.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
### Licensing Information
License is a one-page document as defined by QualComm. Please read the license document in detail before using this dataset [here](https://developer.qualcomm.com/downloads/data-license-agreement-research-use?referrer=node/68935).
### Citation Information
```bibtex
@inproceedings{goyal2017something,
title={The" something something" video database for learning and evaluating visual common sense},
author={Goyal, Raghav and Ebrahimi Kahou, Samira and Michalski, Vincent and Materzynska, Joanna and Westphal, Susanne and Kim, Heuna and Haenel, Valentin and Fruend, Ingo and Yianilos, Peter and Mueller-Freitag, Moritz and others},
booktitle={Proceedings of the IEEE international conference on computer vision},
pages={5842--5850},
year={2017}
}
```
### Contributions
Thanks to [@apsdehal](https://github.com/apsdehal) for adding this dataset. | 15,487 | [
[
-0.032196044921875,
-0.05120849609375,
0.0263824462890625,
0.01190185546875,
-0.009246826171875,
0.0137481689453125,
0.01322174072265625,
-0.01294708251953125,
0.04327392578125,
0.0163116455078125,
-0.0697021484375,
-0.04010009765625,
-0.05224609375,
-0.0153... |
bigscience-data/roots_en_wikiversity | 2022-12-12T11:02:58.000Z | [
"language:en",
"license:cc-by-sa-3.0",
"region:us"
] | bigscience-data | null | null | 0 | 11 | 2022-05-18T09:08:31 | ---
language: en
license: cc-by-sa-3.0
extra_gated_prompt: 'By accessing this dataset, you agree to abide by the BigScience
Ethical Charter. The charter can be found at:
https://hf.co/spaces/bigscience/ethical-charter'
extra_gated_fields:
I have read and agree to abide by the BigScience Ethical Charter: checkbox
---
ROOTS Subset: roots_en_wikiversity
# wikiversity_filtered
- Dataset uid: `wikiversity_filtered`
### Description
### Homepage
### Licensing
### Speaker Locations
### Sizes
- 0.0367 % of total
- 0.1050 % of en
- 0.1178 % of fr
- 0.1231 % of pt
- 0.0072 % of zh
- 0.0393 % of es
- 0.0076 % of ar
- 0.0069 % of indic-hi
### BigScience processing steps
#### Filters applied to: en
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_en
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_1024
#### Filters applied to: fr
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_fr
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_1024
#### Filters applied to: pt
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_pt
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_300
#### Filters applied to: zh
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_zhs
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_1024
#### Filters applied to: es
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_es
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_1024
#### Filters applied to: ar
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_ar
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_300
#### Filters applied to: indic-hi
- filter_wiki_user_titles
- filter_wiki_non_text_type
- dedup_document
- filter_remove_empty_docs
- split_sentences_indic-hi
- dedup_template_soft
- replace_newline_with_space
- filter_small_docs_bytes_300
| 2,318 | [
[
-0.046051025390625,
-0.03338623046875,
0.0183258056640625,
0.01425933837890625,
-0.009918212890625,
-0.00588226318359375,
-0.01534271240234375,
-0.0005488395690917969,
0.046295166015625,
0.033599853515625,
-0.059783935546875,
-0.05780029296875,
-0.04910278320312... |
silver/personal_dialog | 2022-07-10T13:05:21.000Z | [
"task_categories:conversational",
"task_ids:dialogue-generation",
"annotations_creators:no-annotation",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:10M<n<100M",
"source_datasets:original",
"language:zh",
"license:other",
"arxiv:1901.09672",
"region:us"
] | silver | The PersonalDialog dataset is a large-scale multi-turn Chinese dialogue dataset containing various traits from a large number of speakers.
We are releasing about 5M sessions of carefully filtered dialogues.
Each utterance in PersonalDialog is associated with a speaker marked with traits like Gender, Location, Interest Tags. | @article{zheng2019personalized,
title = {Personalized dialogue generation with diversified traits},
author = {Zheng, Yinhe and Chen, Guanyi and Huang, Minlie and Liu, Song and Zhu, Xuan},
journal = {arXiv preprint arXiv:1901.09672},
year = {2019}
}
@inproceedings{zheng2020pre,
title = {A pre-training based personalized dialogue generation model with persona-sparse data},
author = {Zheng, Yinhe and Zhang, Rongsheng and Huang, Minlie and Mao, Xiaoxi},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {34},
number = {05},
pages = {9693--9700},
year = {2020}
} | 13 | 11 | 2022-05-29T14:23:58 | ---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- zh
license:
- other
multilinguality:
- monolingual
paperswithcode_id: personaldialog
pretty_name: "PersonalDialog"
size_categories:
- 10M<n<100M
source_datasets:
- original
task_categories:
- conversational
task_ids:
- dialogue-generation
---
# Dataset Card for PersonalDialog
## Table of Contents
- [Dataset Card for PersonalDialog](#dataset-card-for-personaldialog)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.zhengyinhe.com/datasets/
- **Repository:** https://github.com/silverriver/PersonalDilaog
- **Paper:** https://arxiv.org/abs/1901.09672
### Dataset Summary
The PersonalDialog dataset is a large-scale multi-turn Chinese dialogue dataset containing various traits from a large number of speakers.
We are releasing about 5M sessions of carefully filtered dialogues.
Each utterance in PersonalDialog is associated with a speaker marked with traits like Gender, Location, Interest Tags.
### Supported Tasks and Leaderboards
- dialogue-generation: The dataset can be used to train a model for generating dialogue responses.
- response-retrieval: The dataset can be used to train a reranker model that can be used to implement a retrieval-based dialogue model.
### Languages
PersonalDialog is in Chinese
PersonalDialog中的对话是中文的
## Dataset Structure
### Data Instances
`train` split:
```json
{
"dialog": ["那么 晚", "加班 了 刚 到 家 呀 ！", "吃饭 了 么", "吃 过 了 ！"],
"profile": [
{
"tag": ["间歇性神经病", "爱笑的疯子", "他们说我犀利", "爱做梦", "自由", "旅游", "学生", "双子座", "好性格"],
"loc": "福建 厦门", "gender": "male"
}, {
"tag": ["设计师", "健康养生", "热爱生活", "善良", "宅", "音樂", "时尚"],
"loc": "山东 济南", "gender": "male"
}
],
"uid": [0, 1, 0, 1],
}
```
`dev` and `test` split:
```json
{
"dialog": ["没 人性 啊 ！", "可以 来 组织 啊", "来 上海 陪姐 打 ？"],
"profile": [
{"tag": [""], "loc": "上海 浦东新区", "gender": "female"},
{"tag": ["嘉庚", "keele", "leicester", "UK", "泉州五中"], "loc": "福建 泉州", "gender": "male"},
],
"uid": [0, 1, 0],
"responder_profile": {"tag": ["嘉庚", "keele", "leicester", "UK", "泉州五中"], "loc": "福建 泉州", "gender": "male"},
"golden_response": "吴经理 派车来 小 泉州 接 么 ？",
"is_biased": true,
}
```
### Data Fields
- `dialog` (list of strings): List of utterances consisting of a dialogue.
- `profile` (list of dicts): List of profiles associated with each speaker.
- `tag` (list of strings): List of tags associated with each speaker.
- `loc` (string): Location of each speaker.
- `gender` (string): Gender of each speaker.
- `uid` (list of int): Speaker id for each utterance in the dialogue.
- `responder_profile` (dict): Profile of the responder. (Only available in `dev` and `test` split)
- `golden_response` (str): Response of the responder. (Only available in `dev` and `test` split)
- `id_biased` (bool): Whether the dialogue is guranteed to be persona related or not. (Only available in `dev` and `test` split)
### Data Splits
|train|valid|test|
|---:|---:|---:|
|5,438,165 | 10,521 | 10,523 |
## Dataset Creation
### Curation Rationale
[Needs More Information]
### Source Data
#### Initial Data Collection and Normalization
[Needs More Information]
#### Who are the source language producers?
[Needs More Information]
### Annotations
#### Annotation process
[Needs More Information]
#### Who are the annotators?
[Needs More Information]
### Personal and Sensitive Information
[Needs More Information]
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[Needs More Information]
### Licensing Information
other-weibo
This dataset is collected from Weibo.
You can refer to the [detailed policy](https://weibo.com/signup/v5/privacy) required to use this dataset.
Please restrict the usage of this dataset to non-commerical purposes.
### Citation Information
```bibtex
@article{zheng2019personalized,
title = {Personalized dialogue generation with diversified traits},
author = {Zheng, Yinhe and Chen, Guanyi and Huang, Minlie and Liu, Song and Zhu, Xuan},
journal = {arXiv preprint arXiv:1901.09672},
year = {2019}
}
@inproceedings{zheng2020pre,
title = {A pre-training based personalized dialogue generation model with persona-sparse data},
author = {Zheng, Yinhe and Zhang, Rongsheng and Huang, Minlie and Mao, Xiaoxi},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {34},
number = {05},
pages = {9693--9700},
year = {2020}
}
```
### Contributions
Thanks to [Yinhe Zheng](https://github.com/silverriver) for adding this dataset.
| 6,190 | [
[
-0.035491943359375,
-0.061370849609375,
0.013702392578125,
0.00775146484375,
-0.0001341104507446289,
0.0057220458984375,
-0.023773193359375,
-0.01373291015625,
0.0201568603515625,
0.042236328125,
-0.07257080078125,
-0.051544189453125,
-0.017547607421875,
0.0... |
GEM/squality | 2022-10-25T12:58:23.000Z | [
"task_categories:summarization",
"annotations_creators:crowd-sourced",
"language_creators:unknown",
"multilinguality:unknown",
"size_categories:unknown",
"source_datasets:original",
"language:en",
"license:cc-by-4.0",
"arxiv:2205.11465",
"arxiv:2112.07637",
"arxiv:2104.05938",
"region:us"
] | GEM | This new dataset is designed to solve this great NLP task and is crafted with a lot of care. | @article{wang2022squality,
title={{SQ}u{ALITY}: Building a Long-Document Summarization Dataset the Hard Way},
author={Wang, Alex and Pang, Richard Yuanzhe and Chen, Angelica and Phang, Jason and Bowman, Samuel R.},
journal={arXiv preprint 2205.11465},
year={2022}
} | 1 | 11 | 2022-05-29T16:40:50 | ---
annotations_creators:
- crowd-sourced
language_creators:
- unknown
language:
- en
license:
- cc-by-4.0
multilinguality:
- unknown
size_categories:
- unknown
source_datasets:
- original
task_categories:
- summarization
task_ids: []
pretty_name: squality
---
# Dataset Card for GEM/squality
## Dataset Description
- **Homepage:** https://github.com/nyu-mll/SQuALITY
- **Repository:** https://github.com/nyu-mll/SQuALITY/data
- **Paper:** https://arxiv.org/abs/2205.11465
- **Leaderboard:** N/A
- **Point of Contact:** Alex Wang
### Link to Main Data Card
You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/squality).
### Dataset Summary
SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a summarization dataset that is:
* Abstractive
* Long-input: The input document are short stories between 3000--6000 words.
* Question-focused: Each story is associated with multiple question-summary pairs.
* Multi-reference: Each question is paired with 4 summaries.
* High-quality: The summaries are crowdsourced from skilled and trained writers.
You can load the dataset via:
```
import datasets
data = datasets.load_dataset('GEM/squality')
```
The data loader can be found [here](https://huggingface.co/datasets/GEM/squality).
#### website
[Github](https://github.com/nyu-mll/SQuALITY)
#### paper
[ArXiv](https://arxiv.org/abs/2205.11465)
#### authors
Alex Wang (NYU); Angelica Chen (NYU); Richard Yuanzhe Pang (NYU); Nitish Joshi (NYU); Samuel R. Bowman (NYU)
## Dataset Overview
### Where to find the Data and its Documentation
#### Webpage
<!-- info: What is the webpage for the dataset (if it exists)? -->
<!-- scope: telescope -->
[Github](https://github.com/nyu-mll/SQuALITY)
#### Download
<!-- info: What is the link to where the original dataset is hosted? -->
<!-- scope: telescope -->
[Github](https://github.com/nyu-mll/SQuALITY/data)
#### Paper
<!-- info: What is the link to the paper describing the dataset (open access preferred)? -->
<!-- scope: telescope -->
[ArXiv](https://arxiv.org/abs/2205.11465)
#### BibTex
<!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. -->
<!-- scope: microscope -->
```
@article{wang2022squality,
title={S{Q}u{ALITY}: Building a Long-Document Summarization Dataset the Hard Way},
author={Wang, Alex and Pang, Richard Yuanzhe and Chen, Angelica and Phang, Jason and Bowman, Samuel R.},
journal={arXiv preprint 2205.11465},
year={2022}
}
```
#### Contact Name
<!-- quick -->
<!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
Alex Wang
#### Contact Email
<!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
wangalexc@gmail.com
#### Has a Leaderboard?
<!-- info: Does the dataset have an active leaderboard? -->
<!-- scope: telescope -->
no
### Languages and Intended Use
#### Multilingual?
<!-- quick -->
<!-- info: Is the dataset multilingual? -->
<!-- scope: telescope -->
no
#### Covered Dialects
<!-- info: What dialects are covered? Are there multiple dialects per language? -->
<!-- scope: periscope -->
stories: 1930--1970 American English
summaries: modern American English
#### Covered Languages
<!-- quick -->
<!-- info: What languages/dialects are covered in the dataset? -->
<!-- scope: telescope -->
`English`
#### Whose Language?
<!-- info: Whose language is in the dataset? -->
<!-- scope: periscope -->
stories: 1930--1970 American science fiction writers (predominantly American men)
summaries: Upwork writers (college-educated, native-English) and NYU undergraduates (English-fluent college students)
#### License
<!-- quick -->
<!-- info: What is the license of the dataset? -->
<!-- scope: telescope -->
cc-by-4.0: Creative Commons Attribution 4.0 International
#### Intended Use
<!-- info: What is the intended use of the dataset? -->
<!-- scope: microscope -->
summarization research
#### Primary Task
<!-- info: What primary task does the dataset support? -->
<!-- scope: telescope -->
Summarization
#### Communicative Goal
<!-- quick -->
<!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. -->
<!-- scope: periscope -->
Given a question about a particular high-level aspect of a short story, provide a summary about that aspect in the story (e.g., plot, character relationships, setting, theme, etc.).
### Credit
#### Curation Organization Type(s)
<!-- info: In what kind of organization did the dataset curation happen? -->
<!-- scope: telescope -->
`academic`
#### Curation Organization(s)
<!-- info: Name the organization(s). -->
<!-- scope: periscope -->
New York University
#### Dataset Creators
<!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). -->
<!-- scope: microscope -->
Alex Wang (NYU); Angelica Chen (NYU); Richard Yuanzhe Pang (NYU); Nitish Joshi (NYU); Samuel R. Bowman (NYU)
#### Funding
<!-- info: Who funded the data creation? -->
<!-- scope: microscope -->
Eric and Wendy Schmidt; Apple; NSF
#### Who added the Dataset to GEM?
<!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. -->
<!-- scope: microscope -->
Alex Wang (NYU)
### Dataset Structure
#### Data Fields
<!-- info: List and describe the fields present in the dataset. -->
<!-- scope: telescope -->
* metadata: Project Gutenberg ID, internal UID, Project Gutenberg license
* document: the story
* questions: a list where each element contains
* question text: the question
* question number: the order in which workers answered the question
* responses: a list where each element contains
* worker ID: anonymous
* internal UID
* response text: the response
#### Reason for Structure
<!-- info: How was the dataset structure determined? -->
<!-- scope: microscope -->
The dataset is arranged with responses grouped by question (for ease of multi-reference training and evaluation) and questions grouped by story (to avoid duplicating the story in the dataset)
#### Example Instance
<!-- info: Provide a JSON formatted example of a typical instance in the dataset. -->
<!-- scope: periscope -->
```
{"metadata": {"passage_id": "63833", "uid": "ea0017c487a245668698cf527019b2b6", "license": ""}, "document": "Story omitted for readability", "questions": [{"question_text": "What is the plot of the story?", "question_number": 1, "responses": [{"worker_id": "6", "uid": "0c27bef1b7b644ffba735fdb005f9529", "response_text": "Brevet Lieutenant Commander David Farragut Stryakalski III, AKA Strike, is charged with commanding a run-down and faulty vessel, the Aphrodite. Aphrodite was the brain-child of Harlan Hendricks, an engineer who ushered in new technology ten years back. All three of his creations failed spectacularly, resulting in death and a failed career. The Aphrodite was the only ship to survive, and she is now used for hauling mail back and forth between Venus and Mars.\nStrike and Cob, the Aphrodite\u2019s only executive to last more than six months, recount Strike\u2019s great failures and how he ended up here. He used to fly the Ganymede, but was removed after he left his position to rescue colonists who didn\u2019t need rescuing. Strike was no longer trustworthy in Admiral Gorman\u2019s eyes, so he banished him to the Aphrodite. \nThe circuit that caused the initial demise of Aphrodite was sealed off. After meeting some members of his crew, Strike orders a conference for all personnel and calls in an Engineering Officer, one I.V. Hendricks. \nAfter Lieutenant Ivy Hendricks arrives--not I.V.--Strike immediately insults her by degrading the ship\u2019s designer, Harlan Hendricks. As it turns out, Hendricks is his daughter, and she vows to prove him wrong and all those who doubted her father. \nDespite their initial conflict, Strike and Hendricks\u2019 relationship soon evolves from resentment to respect. During this time, Strike\u2019s confidence in the Aphrodite plummets as she suffers from mechanical issues. \nThe Aphrodite starts to heat up as they get closer to the sun. The refrigeration units could not handle the heat, causing discomfort among the crew. As they get closer, a radar contact reveals that two dreadnaughts, the Lachesis and the Atropos, are doing routine patrolling. Nothing to worry about, except the Atropos had Admiral Gorman on board, hated by Strike and Hendricks.\nStrike and Hendricks make a joke about Gorman falling into the sun. As the temperature steadily climbs, the crew members overheat and begin fighting, resulting in a black eye. A distress signal came through from the Lachesis: the Atropos, with Gorman on board, was tumbling into the sun. The Lachesis was attempting to rescue them with an unbreakable cord, but they too were being pulled in. \nHendricks had fixed the surge-circuit rheostat, the one her father designed, and claimed it could help them rescue the ships. After some tension, Strike agrees and they race down to the sun to pick up the drifting dreadnaughts. \nStrike puts Hendricks in charge, but soon the heat overtakes her, and she is unable to continue. Strike takes over, attaches the Aphrodite to the Lachesis with a cord, and turns on the surge-circuit. They blast themselves out of there, rescuing the two ships and Admiral Gorman at the same time. \nCob and Strike are awarded Spatial Cross awards, while Hendricks is promoted to an engineering position at the Bureau of Ships. The story ends with Cob and Strike flipping through the pages of an address book until they land on Canalopolis, Mars. \n"}, {"worker_id": "1", "uid": "04e79312dede4a0da5993101e55a796a", "response_text": "Strike joins the crew of the Aphrodite after he has made several poor decisions while he was the captain of another spaceship. He is essentially being punished by his boss, Gorman, and put somewhere where he can do little harm. His job is to deliver the mail from Venus to Mars, so it\u2019s pretty straightforward. \n\nWhen he meets the Officer of the Deck, Celia Graham, he immediately becomes uncomfortable. He does not like to work with women in space, although it\u2019s a pretty common occurrence. He holds a captain\u2019s meeting the first day on the job, and he waits to meet his Engineering Officer, I.V. Hendricks. He makes a rude comment about how the man is late for his first meeting, but actually, the female Ivy has already shown up. \n\nAfter meeting Ivy formally, he makes a comment about how the ship Aphrodite was built by an imbecile. Ivy immediately tells him that he\u2019s wrong, and she knows this because the designer of the ship was none other than her own father. \n\nHis first week as captain on the new ship goes very poorly. Several repairs need to be done to Aphrodite, they run behind schedule, and the new crew members have a tough time getting a handle on Aphrodite\u2019s intricacies. \n\nThe heat index in the ship begins to rise, and the crew members can no longer wear their uniforms without fainting. Suddenly a distress call comes in, and it\u2019s coming from the Atropos, a ship Captained by Gorman, and the Lachesis. The crew members hesitate to take the oldest and most outdated machinery on a rescue trip. Strike has been in trouble for refusing to follow commands before, and he knows it\u2019s a risky move. However, Ivy insists that she knows how to pilot the Aphrodite, and she can save the crew members on the Atropos and the Lachesis from death. They are quickly tumbling towards the sun, and they will perish if someone doesn\u2019t do something quickly. \n\nIvy takes control of the ship, and the heat on the Aphrodite continues to rise steadily. Eventually, she faints from pure heat exhaustion, and she tells Strike that he must take over. He does, and he manages to essentially lasso the other two ships, and with just the right amount of power, he pulls them back into orbit. \n\nAt a bar, after the whole ordeal, Cob pokes fun at Strike for staying on the Aphrodite. He then admits that he actually respects Strike\u2019s loyalty to the ship that saved his reputation. Cob asks about Strike\u2019s relationship with Ivy, but Strike tells him that she has taken her dad\u2019s former job, so she no longer works with him. Strike takes the moment to look up her info, presumably to restart the relationship. \n"}, {"worker_id": "5", "uid": "71efb8636b504f42a6989bb90e360186", "response_text": "The narrative follows commander Strike as he begins his command of the spaceship Aphrodite. Strike comes from a long line of military greats but himself is prone to poor professional decision making.\n\nAs he takes command, the mission is a simple mail run. However, in the course of their journey, they receive word of two ships in dire need of rescue. Strike and his engineering officer, Ivy Hendricks, decide to use the ships extremely risky surge-circuit to aid the ships.\n\nThe rescue is a success and the crew is hailed for its bravery in saving the doomed vessels. "}, {"worker_id": "3", "uid": "8aa46ba8bd2945c98babd7dd2d9ecc38", "response_text": "The story starts in a muddy swamp on Venus, where Strike, a Brevet Lieutenant Commander, is encountering his new ship, the Aphrodite, for the first time. Here on Venusport Base, he is introduced to the executive officer of the ship, a man who goes by Cob. Strike comes from a line of servicemen who were all well respected, but he himself has more of a reputation for causing trouble by saying the wrong things or deviating from mission plans. His reputation preceded him, as Cob had specific questions about some of these events. The Aphrodite was incredibly impressive when it was designed, but did not live up to its expectations. It had been refitted, and the new mission that Strike was to lead was a mail run between Venus and Mars. As he entered the ship, Strike began to meet his new crew, including Celia Graham, his Radar Officer. Strike is not used to women being on ships and is decidedly uncomfortable with the idea. As he is briefing the officers who were already present, Strike is surprised when he meets his new engineering officer, Ivy Hendricks. Ivy is the daughter of the man who designed the ship, and she is cold to Strike at first, as he is to her. However, her expertise in engineering generally, the ship specifically, and other skills as well as piloting, meant that Strike warmed up to her as their mission went on. As the ship was flying towards Mars on their route, the crew picked up a distress signal from the Lachesis, which was trying to pull the Atropos away from the gravitational pull of the sun after it was damaged in an equipment malfunction. The Admiral who had put Strike in charge of the Aphrodite was on the Atropos, and Ivy dislikes him even more than Strike does, but they know they have to try to save the crews. Strike is hesitant, but Ivy has a plan and insists that they try. She has spent all of her free time tinkering with the circuits, and takes charge. She turned the Aphrodite towards the ships in danger, and sends out a cable to connect the Aphrodite to those ships. After they are all connected, the ships continue to spin towards the sun, which causes Ivy to pass out, leaving Strike in charge. He manages to pull the ships into line and send the Aphrodite in the right direction before passing out himself. The Aphrodite has the power to pull everyone away from the Sun\u2019s gravity, but the acceleration knocks everyone out on all three ships. In the end, it was a successful rescue mission of multiple crews. Strike and Cob find themselves in an officer\u2019s club at the end of the story, discussing Ivy\u2019s new job, and Strike acknowledges that Cob is right about the Aphrodite having grown on him, and plans to stay its captain."}]}, {"question_text": "Who is Ivy Hendricks and what happens to her throughout the story?", "question_number": 2, "responses": [{"worker_id": "6", "uid": "0c27bef1b7b644ffba735fdb005f9529", "response_text": "Lieutenant Ivy Hendricks is the daughter of Harlan Hendricks, a formerly respected engineer. He created the surge-circuit, an innovation in interstellar astrogation, and he was awarded a Legion of Merit. He designed three famous ships: the Artemis, the Andromeda, and the Aphrodite, the prototype. Despite being hailed as the latest and greatest in technology, all three ships either exploded or failed. \nAccording to Lieutenant Ivy Hendricks, their failures were due to the lack of education on board. She claimed that her father asked for the crew members to be trained in surge-circuit technology, so they could use it properly and correctly. That wish was not granted and after all three ships failed, his reputation and career were doomed. Admiral Gorman pulled the plug on his career and therefore became the target of all Lieutenant Hendricks\u2019 hate. \nWith a bone to pick, Lieutenant Hendricks, a knowledgeable engineer herself, comes aboard the Aphrodite to serve as her engineer and occasional pilot. She wants to prove to the world that her father\u2019s creation was genius and deserving of praise. \nAlthough they started off on the wrong foot, Lieutenant Hendricks and Strike, her commander, develop a friendship and appreciation for each other. They bond over their deep hatred of Admiral Gorman and the joy of piloting a ship. She soon proves herself to Strike, and he begins to trust her. Their relationship walks the fine line between friendship and romance. \nAs the Aphrodite is attempting to rescue the fallen dreadnaughts, Lieutenant Hendricks comes up with the solution. Due to her constant tinkering on the ship, she had fixed the surge-circuit rheostat and made it ready to use. Initially, no one trusts her, seeing as the last time it was used people died. But Strike\u2019s trust in her is strong and true, so he approves the use of the surge-circuit. Hendricks pilots the ship, but soon becomes too overheated and comes close to fainting. Strike takes over piloting and eventually activates the surge-circuit. It works and they are able to rescue the two ships, one of which had Admiral Gorman, her sworn enemy, onboard. \nLieutenant Hendricks receives a major promotion; she is now an engineer at the Bureau of Ships. She proved them wrong, and restored her father\u2019s legacy and good name. The story ends with their romance left in the air, but Hendricks has much to be proud of. \n"}, {"worker_id": "1", "uid": "04e79312dede4a0da5993101e55a796a", "response_text": "\nLieutenant Ivy Hendricks is the new Engineering Officer on Aphrodite. Strike and Cob assume that Ivy is a man before she arrives because they are sexist and because her name is listed as I.V. in the orders. Ivy is actually the daughter of the man who designed the award-winning craft.\n\nShe is cold and unfriendly towards Strike after she meets him, and that\u2019s probably because he makes a rude comment about the ship which her father created. After a couple weeks of working together, the two begin to get along very well. Strike admires Ivy\u2019s piloting skills and her depth of knowledge about the Aphrodite. \n\nThe two also bond over their shared hatred of Strike\u2019s former boss, Gorman. Strike feels as though he has ruined his career, and Ivy thinks that Gorman torpedoed her father\u2019s career. Ivy wants nothing more than to prove that Gorman is an idiot. \n\nHowever, when Gorman\u2019s ship is hurtling towards the sun and he and his crew members are about to die, Ivy sees that it\u2019s the perfect opportunity to show Gorman just how wrong he was about the ship her father designed. It\u2019s a very dangerous mission, but Ivy is steadfast in her decision and she\u2019s deeply courageous. She pilots the ship for most of the rescue mission, but eventually faints from the extreme heat. She tells Strike that he needs to take over, and he does a great job. \n\nIvy is then promoted, and she moves to Canalopolis, Mars. She now outranks her former Captain, Strike. \n"}, {"worker_id": "5", "uid": "71efb8636b504f42a6989bb90e360186", "response_text": "Ivy Hendricks is the engineering officer assigned to the Aphrodite. She is the daughter of Harlan Hendricks, the ship's original designer. She is fiercely protective of her father's legacy and resents Admiral Gorman for the way he treated him.\n\nHendricks and Strike, form an alliance of sorts after his initial surprise of seeing a woman assigned to this officer's role. When news arrives that two ships are in danger of falling into the sun, Ivy lobbies to use her father's technology to save the ship. Strike agrees to her plan although the risks are high. The Aphrodite eventually saves the ships although Ivy faints in the process from the heat and command has to be taken over by Strike.\n\nThe successful mission results in a promotion for Ivy as she works as a designer in the Bureau of Ships like her father."}, {"worker_id": "3", "uid": "8aa46ba8bd2945c98babd7dd2d9ecc38", "response_text": "Ivy Hendricks is the new engineering officer on the Aphrodite, having been transferred from the Antigone. She is a tall woman with dark hair and contrasting pale blue eyes, who has a very wide range of experience in ship operations and engineering. Her father, Harlan Hendricks, was the man who designed the Aphrodite, so she knows the ship needs a lot of specific training. At first, the captain did not expect her to be a woman, and managed to imply that many people found her father incompetent. Although she seemed cold at first, as she reacted to the situation, she and the captain eventually got along fairly well, as he learned to appreciate her wide skill set that ranged from engineering to piloting. Ivy and Strike also had a common enemy in the higher ranks: Space Admiral Gorman. Once Spike trusted her he appreciated that Ivy spent a lot of spare time working on the old circuits, so she knew the ship like the back of her hand. When the Aphrodite found the Lachesis and the Atropos when following up on a distress signal, Ivy new the ship well enough to be able to formulate a plan to save everyone. She piloted the Aphrodite carefully, using cables shot with a rocket to connect the three ships together, but the spinning of the ships in the heat inside meant that she passed out and had to leave Strike to take over for her. Her plan was successful; she was promoted, and instead of returning to the Aphrodite she started a design job with the Bureau of Ships."}]}, {"question_text": "What is the relationship between Strike and Aphrodite?", "question_number": 3, "responses": [{"worker_id": "6", "uid": "0c27bef1b7b644ffba735fdb005f9529", "response_text": "Strike is a member of a famous, well-behaved, and well-trained service family. His father and grandfather served in World War II and the Atomic War, respectively. Both earned medals for their heroic service. Strike, however, did not follow in his family\u2019s footsteps. \n\tWith a tendency to say the wrong thing at the wrong time, Strike often offended those around him and garnered a negative reputation. After being put in charge of the Ganymede, he soon lost his position after abandoning his station to rescue colonists who were not in danger. As well, he accused a Martian Ambassador of being a spy at a respectable ball. Admiral Gorman soon demoted him, and he became the commander of the Aphrodite. \n\tAt first, Strike was not a fan. He sees her as ugly, fat, and cantankerous. He misses the Ganymede, a shiny and new rocketship, and views the Aphrodite as less-than. \n\tWithin the first week of flying her, the Aphrodite had a burned steering tube, which made it necessary to go into free-fall as the damage control party made repairs. Strike\u2019s faith in Lover-Girl continued to plummet. \n\tHowever, after Lieutenant Hendricks, the resident engineer, got her hands on the Aphrodite, Strike\u2019s opinion started to change. Her knowledge of the ship, engineering, and piloting helped him gain confidence in both her abilities and those of Aphrodite.\nNear the end of the story, the Aphrodite is tasked with rescuing two ships that are falling into the sun. Previously Lieutenant Hendricks had fixed up the surge-circuit rheostat, and so she offered it up as the only solution. Strike agrees to try it, which shows his faith and trust in the Aphrodite. Luckily, all things go to plan, and the Aphrodite, with Strike piloting, is able to save the two ships and Admiral Gorman. \nAfter Strike won a medal himself, finally following in the family footsteps, he is offered his old position back on the Ganymede. He refuses, and instead returns to old Lover-Girl. He has grown fond of her over the course of their adventure, and they develop a partnership. "}, {"worker_id": "1", "uid": "04e79312dede4a0da5993101e55a796a", "response_text": "Strike is completely unimpressed by the rocket ship Aphrodite. He comments that she looks like a pregnant carp, and he knows that he\u2019s been assigned captain of the ship because he messed up terribly on his other missions. \n\nAphrodite was built 10 years ago, and now she is completely outdated and a laughing stock compared to the other spaceships in the fleet. She was designed by Harlan Hendricks, and the engineer received a Legion of Merit award for her design. \n\nStrike\u2019s mission is to fly Aphrodite to take the mail from Venusport to Canalopolis, Mars. It\u2019s boring and straightforward.\n\nWhen a disaster occurs and two other ships, the Atropos and the Lachesis, are in serious danger of getting too close to the sun, Strike agrees to take the old girl on a rescue mission. He is convinced by Ivy, since she knows the ship better than anyone else and she believes in her. \n\nAlthough Ivy takes Aphrodite most of the way there, its Strike who finishes the mission and saves his former boss, Gorman, and many other people from certain death. Aphrodite is the entire reason that Strike is able to mend his terrible reputation and he wins back respect from Gorman. Although they got off to a rocky start, Strike finds it impossible to leave his best girl, even when he is offered a job on another ship. He is loyal to the ship that made him a hero. \n"}, {"worker_id": "5", "uid": "71efb8636b504f42a6989bb90e360186", "response_text": "Strike is assigned to be commander of the spaceship Aphrodite. The ship is assigned as a mail carrier for the inner part of the solar system. The Aphrodite is a dilapidated design with an awful reputation. Strike ended up with the Aphrodite as a result of a series of poor professional decisions that resulted in him getting command of the more prestigious ship Ganymede taken away from him.\n\nHis initial impression of the Aphrodite softens to a grudging respect after the successful mission to save the Atropos and Lachesis. Although he presumably is in line to command the Ganymede again, another faux pas resulting in Strike continuing to command the Aphrodite. "}, {"worker_id": "3", "uid": "8aa46ba8bd2945c98babd7dd2d9ecc38", "response_text": "At the beginning of the story, Strike is very reluctant to accept Aphrodite, because being in charge of the ship means a demotion for him. His perception of the ship at the beginning of the story is colored by this history, and his first impression of the ship is not a positive one, even from the outside. Besides the actual construction of the ship, the technology that ran it was not something he showed much faith in. The first week that he was in charge after leaving Venus, it seemed things were going drastically wrong. When one important piece of equipment burnt out, the ship went into freefall, requiring a lot of repair work from the engineers, and anyone in charge of navigation was handed more work because of this as well. The ship was really put to the test when the Aphrodite responded to the distress call from the Lachesis, whose crew was trying to keep the Atropos from falling into the sun. Because Ivy knew the Aphrodite so well, and had been working on the circuits, it turned out the Aphrodite was the perfect ship to save the day. She could not see the rescue all the way through to the end, because she passed out early, but Strike was conscious a little bit longer and took over until he also passed out. After this unexpected rescue mission, Cob, the Executive Officer, noted that Strike has a newfound appreciation for the ship, and has no intention of leaving. Strike is dedicated to his new mission, even though at the beginning of the story he wanted nothing more than to pilot something the same rank as his old ship."}]}, {"question_text": "Describe the setting of the story.", "question_number": 4, "responses": [{"worker_id": "6", "uid": "0c27bef1b7b644ffba735fdb005f9529", "response_text": "Jinx Ship to the Rescue by Alfred Coppel, Jr. takes place in space, but more specifically in the Aphrodite. \n\tIt starts in the muddy Venusport Base on Venus. Venusport is famous for its warm, slimy, and green rain that falls for 480 hours of every day. A fog rolls in and degrades visibility. \n\tDespite starting on Venusport Base, the characters actually spend most of their time onboard the Aphrodite, a Tellurian Rocket Ship. The Aphrodite had a surge-circuit monitor of twenty guns built into her frame. She was bulky, fat, and ugly, and occasionally had some technical and mechanical struggles as well. \n\tAlthough her frame may not be appealing, she soon becomes victorious as she gains the trust of Strike and other members of his crew and saves two fallen dreadnaughts. With her surge-circuit rheostat rebuilt, the Aphrodite is finally able to accomplish what she was always meant to. "}, {"worker_id": "1", "uid": "04e79312dede4a0da5993101e55a796a", "response_text": "The story starts on the planet of Venus. Venus has days that are 720 hours long, and rain is common. The rain is hot, slimy, and green, and it makes the already wet swamplands even more mushy. Fog is common on Venus.\n\nThe middle of the story takes place on the old and outdated ship, Aphrodite. She gives the crew members a lot of trouble on their first mission. She is in dire need of repairs, she\u2019s slow, and it\u2019s impossible to control her temperature. The crew members are unable to wear their uniforms because the temperature is over 100 degrees. \n\nAphrodite\u2019s mission is simple. She needs to take the mail from Venus to Mars, and it\u2019s the only thing she can be trusted to do successfully. So it\u2019s very impressive when she ends up being the hero of the day and manages to rescue two other ships that are headed towards the sun. \n"}, {"worker_id": "5", "uid": "71efb8636b504f42a6989bb90e360186", "response_text": "The narrative is set in the early 21st century primarily aboard the spaceship Aphrodite. The ship's mission is to deliver mail in the inner part of the solar system.\n\nThe ships route takes them around the sun and as a result the ambient temperature inside the ship begins to rise to intolerable levels due to proximity to the sun. Because of the heat, the coed crew is allowed to operate with very little clothing. Aphrodite is a ship of an outdated design that gives it a lack of comfort and subjects it to numerous small problems that make its operation frustrating."}, {"worker_id": "3", "uid": "8aa46ba8bd2945c98babd7dd2d9ecc38", "response_text": "The story starts at a spaceport on Venus, where it has been raining for hundreds of hours straight. The rain has stopped by the time the story starts, but it is left a lot of mud in the swampy marshes. It was nearing the end of the day, and the fog was enveloping the surroundings as it grew darker outside. It was hot and sticky at Venusport Base, but after Strike left the service on his mission in the Aphrodite, it would only grow hotter on board. The ship itself, where most of the story takes place, is an older, refitted, bulky type of ship. There were only two others like it, and their designer had been awarded a Legion of Merit for the three. However, this is the only one still in use, as the others were destroyed in a much earlier mission. Strike\u2019s disappointment in the ship seems to mirror the sentiment. Inside the ship, there are many systems of pipes connected the control panels, and the captain had to navigate carefully so that he didn\u2019t hit his head on the bulkhead. While in space, as the ship flew closer and closer to the sun, the interior of the ship grew hotter and hotter. The crew opted to wear as little clothing as possible in an attempt to handle the heat. When the Aphrodite received the distress call from the Lachesis, the ships were close enough to the sun to be affected by its gravitational pull. After the close call near the sun, once everyone regained consciousness, the story ends at an officer\u2019s club on Mars. It was a formal environment, and the Aphrodite\u2019s captain and executive officer planned the rest of their route from there."}]}, {"question_text": "Who is Strike and what happens to him throughout the story?", "question_number": 5, "responses": [{"worker_id": "6", "uid": "0c27bef1b7b644ffba735fdb005f9529", "response_text": "Strike is a member of an esteemed service family on Venus; seven generations of well-behaved and well-trained operators. Unfortunately, Strike struggles to carry on the family tradition, and is known for misspeaking and offending those around him. By trusting his gut, he wound up failing his higher-ups and crew several times. All this culminated in an eventual mistrust of Strike, which led to him being charged with the Aphrodite. \n\tHis deep hatred of Space Admiral Gordon is passionate, but not without reason. Gordon is the one who demoted him to the Aphrodite. At the start, Strike is checking out his new vessel and notes how ugly the ship is. After examining the ship and it\u2019s crew, it is revealed that Strike is uncomfortable around women and believes they don\u2019t belong on a spaceship. \n\tIn order to start flying, he calls in an expert engineer to come aboard and travel with them. Thinking I.V. Hendricks is a man, he is excited to have them onboard. But when Ivy Hendricks shows up, a female engineer and the daughter of the Aphrodite\u2019s creator, his world is soon turned upside down. \n\tHis initial negative reaction to her is soon displaced by begrudging appreciation and eventually trust and friendship. Hendricks proves his previous theories about women wrong, and Strike is forced to accept that perhaps women do belong on a spaceship. She especially impresses him with her total knowledge of spaceship engineering and the Aphrodite in general. And it helped that she hated Admiral Gorman just as much as Strike, if not more. \n\tWhile flying by the sun to deliver mail, the Aphrodite receives a distress call from two ships: the Lachesis and the Atropos, the latter of which carried Admiral Gorman onboard. After the Aphrodite reached orbit, the Lachesis reached out and reported the Atropos was falling into the sun, due to a burst chamber. They couldn\u2019t move those onboard over thanks to all the radiation, so the Lachesis was attempting to pull the Atropos back using an unbreakable cord. But it wasn\u2019t enough. \n\tSince Ivy Hendricks had fixed the surge-circuit rheostat--the feature that crashed the original Aphrodite--, they were able to save the Lachesis and the Atropos and regain some of their dignity and former glory. \n\tStrike is awarded the Spatial Cross, as well as Cob, his friend and longtime executive of the Aphrodite. Strike was asked to return to the Ganymede, a beautiful sleek ship, but allegedly said the wrong thing to Gorman, and was instead sent back to the Aphrodite. Cob believes he did it on purpose, as Strike had grown quite fond of Lover-Girl. \n\tIvy has gone to the Bureau of Ships to engineer vessels, a great upgrade from her previous job. Cob pressures Strike to reach out to her, but he refuses. However, it ends on a hopeful note, with the potential for romance between Strike and Hendricks, and even more adventures on the clunky Aphrodite. "}, {"worker_id": "1", "uid": "04e79312dede4a0da5993101e55a796a", "response_text": "Strike\u2019s real name is Brevet Lieutenant Commander David Farragut Strykalski III. After serving on the Ganymede, he is put in charge of the Aphrodite. He comes from many generations of officers. However, he doesn\u2019t feel like he fits the mold of his grandfather and great-grandfather and so on. His boss, Gorman, disagreed with several decisions he made in the past and sent him to work on the Aphrodite, the unimpressive spaceship.\n\nStrike does not like working with women in space, so he is disappointed when two of his crew members are powerful and successful females. He learns his lesson after working with Ivy Hendricks for a few weeks. She impresses him with her piloting skills and her knowledge of the ship that her father designed. \n\nStrike is skeptical at first when Ivy wants to take Aphrodite to rescue two ships whose crew members are in grave danger. He knows that the mistakes he made before got him on the Aphrodite, and there\u2019s a big chance that he\u2019ll be fired for trying to save the day, or worse, the mission could end in death for him and all of his crew members. He has feelings for Ivy, and her intense passion convinces him that she\u2019s right, Aphrodite can handle the mission and they can save those peoples\u2019 lives.\n\nIvy pilots the ship almost the entire route, but she is unable to finish the job when she passes out from the intense heat. Captain Strike takes over and saves the crews on the Atropos and the Lachesis. He is hailed as a hero, and he repairs his terrible reputation with the selfless act. He decides not to leave the Aphrodite. He wants to be loyal to the ship that worked so hard for him. He does decide to give Ivy a call. Even though she outranks him, he has to admit that he has a crush on her. "}, {"worker_id": "5", "uid": "71efb8636b504f42a6989bb90e360186", "response_text": "Strike is the commander of the Aphrodite. He was originally the commander of the prestigious Ganymede. However a number of decisions made out of bravado as well as some unprofessional comments lost him that command.\n\nNow in command of a dilapidated ship, Strike comes to terms with his job. He commands a crew including a large number of women which makes him somewhat uncomfortable. His engineering officer Ivy Hendricks in particular seems to be of romantic interest to Strike.\n\nStrike ends up teaming with Ivy to save two ships from falling into the sun earning him a small promotion but an ill-advised comment prevents him from leaving the Aphrodite, perhaps to the satisfaction of Strike himself."}, {"worker_id": "3", "uid": "8aa46ba8bd2945c98babd7dd2d9ecc38", "response_text": "Strike is a highly decorated lieutenant commander in the Navy, who comes from a long line of ship operators. Although he has run many successful missions, he has a reputation of causing trouble\u2014his new Executive Officer, Cob, has heard a number of stories that he asks Strike for details about. Strike has lost command of the ship that he had been captaining, and is sent by Admiral Gorman to captain a mail route on the Aphrodite. He is extremely hesitant to have any positive feelings about the experience, from the ship itself, to the inclusion of women on its crew. Not only is this not the type of ship he is used to, he is never served with women on board. He has to navigate adapting to the new situation while adapting to the new job. Through the first week of his assignment, the ship and its crew grow on him. He comes to trust Ivy Hendricks, the Engineering Officer, and he lets her take charge to try to save the other ships when they respond to a distress call. Eventually, she passes out, and has to leave Strike in charge of getting the ships to safety. Eventually, Strike passes out just like everyone else, from the ship\u2019s acceleration to break the sun\u2019s gravity. At the end of the story, it is clear that his increased appreciation for the ship means he plans on staying, to the delight of his Executive Officer. Cob alludes to Strike having feelings for Ivy, but he says that although she is nice, he has no interest in being with a woman with a higher ranked title than he has. "}]}]}
```
#### Data Splits
<!-- info: Describe and name the splits in the dataset if there are more than one. -->
<!-- scope: periscope -->
train, dev, test
#### Splitting Criteria
<!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. -->
<!-- scope: microscope -->
Stories that appear in both SQuALITY and [QuALITY](https://github.com/nyu-mll/quality) are assigned to the same split in both datasets.
## Dataset in GEM
### Rationale for Inclusion in GEM
#### Why is the Dataset in GEM?
<!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? -->
<!-- scope: microscope -->
The summaries in the dataset were crowdsourced, allowing us to use input documents that are easily understood by crowdworkers (as opposed to technical domains, such as scientific papers). Additionally, there is no lede bias in stories, as is typically in news articles used in benchmark summarization datasets like CNN/DM and XSum.
Additionally, the dataset is multi-reference and the references for each task are highly diverse. Having a diverse set of references better represents the set of acceptable summaries for an input, and opens the door for creative evaluation methodologies using these multiple references.
#### Similar Datasets
<!-- info: Do other datasets for the high level task exist? -->
<!-- scope: telescope -->
yes
#### Unique Language Coverage
<!-- info: Does this dataset cover other languages than other datasets for the same task? -->
<!-- scope: periscope -->
no
#### Difference from other GEM datasets
<!-- info: What else sets this dataset apart from other similar datasets in GEM? -->
<!-- scope: microscope -->
The inputs (story-question pairs) are multi-reference. The questions are high-level and are written to draw from multiple parts of the story, instead of a single section of the story.
### GEM-Specific Curation
#### Modificatied for GEM?
<!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? -->
<!-- scope: telescope -->
no
#### Additional Splits?
<!-- info: Does GEM provide additional splits to the dataset? -->
<!-- scope: telescope -->
no
### Getting Started with the Task
#### Pointers to Resources
<!-- info: Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. -->
<!-- scope: microscope -->
* [original paper](https://arxiv.org/abs/2205.11465)
* [modeling question-focused summarization](https://arxiv.org/abs/2112.07637)
* [similar task format but different domain](https://arxiv.org/abs/2104.05938)
## Previous Results
### Previous Results
#### Metrics
<!-- info: What metrics are typically used for this task? -->
<!-- scope: periscope -->
`ROUGE`, `BERT-Score`
#### Proposed Evaluation
<!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. -->
<!-- scope: microscope -->
Following norms in summarization, we have evaluated with automatic evaluation metrics like ROUGE and BERTScore, but these metrics do not correlate with human judgments of summary quality when comparing model summaries (see paper for details).
We highly recommend users of the benchmark use human evaluation as the primary method for evaluating systems. We present one example of such in the paper in which we ask Upwork workers to read the short story and then rate sets of three responses to each question. While this is close to the gold standard in how we would want to evaluate systems on this task, we recognize that finding workers who will read the whole story (~30m) is difficult and expensive, and doing efficient human evaluation for long document tasks is an open problem.
#### Previous results available?
<!-- info: Are previous results available? -->
<!-- scope: telescope -->
yes
#### Other Evaluation Approaches
<!-- info: What evaluation approaches have others used? -->
<!-- scope: periscope -->
Human evaluation
#### Relevant Previous Results
<!-- info: What are the most relevant previous results for this task/dataset? -->
<!-- scope: microscope -->
See paper (https://arxiv.org/abs/2205.11465)
## Dataset Curation
### Original Curation
#### Sourced from Different Sources
<!-- info: Is the dataset aggregated from different data sources? -->
<!-- scope: telescope -->
no
### Language Data
#### How was Language Data Obtained?
<!-- info: How was the language data obtained? -->
<!-- scope: telescope -->
`Crowdsourced`
#### Where was it crowdsourced?
<!-- info: If crowdsourced, where from? -->
<!-- scope: periscope -->
`Other crowdworker platform`
#### Language Producers
<!-- info: What further information do we have on the language producers? -->
<!-- scope: microscope -->
Upwork: US-born, native English speakers with backgrounds in the humanities and copywriting
NYU undergraduates: English-fluent undergraduates from a diverse set of nationalities and majors
#### Topics Covered
<!-- info: Does the language in the dataset focus on specific topics? How would you describe them? -->
<!-- scope: periscope -->
The short stories are primarily science fiction and from the 1930s -- 1970s.
#### Data Validation
<!-- info: Was the text validated by a different worker or a data curator? -->
<!-- scope: telescope -->
validated by crowdworker
#### Was Data Filtered?
<!-- info: Were text instances selected or filtered? -->
<!-- scope: telescope -->
not filtered
### Structured Annotations
#### Additional Annotations?
<!-- quick -->
<!-- info: Does the dataset have additional annotations for each instance? -->
<!-- scope: telescope -->
crowd-sourced
#### Number of Raters
<!-- info: What is the number of raters -->
<!-- scope: telescope -->
11<n<50
#### Rater Qualifications
<!-- info: Describe the qualifications required of an annotator. -->
<!-- scope: periscope -->
English-fluent, with experience reading and writing about literature
#### Raters per Training Example
<!-- info: How many annotators saw each training example? -->
<!-- scope: periscope -->
4
#### Raters per Test Example
<!-- info: How many annotators saw each test example? -->
<!-- scope: periscope -->
4
#### Annotation Service?
<!-- info: Was an annotation service used? -->
<!-- scope: telescope -->
no
#### Any Quality Control?
<!-- info: Quality control measures? -->
<!-- scope: telescope -->
validated by another rater
#### Quality Control Details
<!-- info: Describe the quality control measures that were taken. -->
<!-- scope: microscope -->
Each response was reviewed by three reviewers, who ranked the response (against two other responses), highlighted errors in the response, and provided feedback to the original response writer.
### Consent
#### Any Consent Policy?
<!-- info: Was there a consent policy involved when gathering the data? -->
<!-- scope: telescope -->
yes
#### Consent Policy Details
<!-- info: What was the consent policy? -->
<!-- scope: microscope -->
Writers were informed that their writing and reviewing would be used in the development of AI.
### Private Identifying Information (PII)
#### Contains PII?
<!-- quick -->
<!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? -->
<!-- scope: telescope -->
unlikely
#### Any PII Identification?
<!-- info: Did the curators use any automatic/manual method to identify PII in the dataset? -->
<!-- scope: periscope -->
no identification
### Maintenance
#### Any Maintenance Plan?
<!-- info: Does the original dataset have a maintenance plan? -->
<!-- scope: telescope -->
no
## Broader Social Context
### Previous Work on the Social Impact of the Dataset
#### Usage of Models based on the Data
<!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? -->
<!-- scope: telescope -->
no
### Impact on Under-Served Communities
#### Addresses needs of underserved Communities?
<!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). -->
<!-- scope: telescope -->
no
### Discussion of Biases
#### Any Documented Social Biases?
<!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. -->
<!-- scope: telescope -->
yes
## Considerations for Using the Data
### PII Risks and Liability
### Licenses
#### Copyright Restrictions on the Dataset
<!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? -->
<!-- scope: periscope -->
`open license - commercial use allowed`
#### Copyright Restrictions on the Language Data
<!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? -->
<!-- scope: periscope -->
`public domain`
### Known Technical Limitations
#### Unsuited Applications
<!-- info: When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? In particular, describe some applications of the general task featured in this dataset that its curation or properties make it less suitable for. -->
<!-- scope: microscope -->
The stories in the dataset are from the 1930--1970s and may contain harmful stances on topics like race and gender. Models trained on the stories may reproduce these stances in their outputs.
#### Discouraged Use Cases
<!-- info: What are some discouraged use cases of a model trained to maximize the proposed metrics on this dataset? In particular, think about settings where decisions made by a model that performs reasonably well on the metric my still have strong negative consequences for user or members of the public. -->
<!-- scope: microscope -->
The proposed automatic metrics for this dataset (ROUGE, BERTScore) are not sensitive to factual errors in summaries, and have been shown to not correlate well with human judgments of summary quality along a number of axes.
| 51,748 | [
[
-0.0240936279296875,
-0.055999755859375,
0.0361328125,
-0.00641632080078125,
-0.01074981689453125,
-0.00994110107421875,
-0.009063720703125,
-0.0298919677734375,
0.043792724609375,
0.02825927734375,
-0.0538330078125,
-0.050201416015625,
-0.0278472900390625,
... |
hugginglearners/malayalam_news | 2022-07-04T06:13:54.000Z | [
"region:us"
] | hugginglearners | The AI4Bharat-IndicNLP dataset is an ongoing effort to create a collection of large-scale,
general-domain corpora for Indian languages. Currently, it contains 2.7 billion words for 10 Indian languages from two language families.
We share pre-trained word embeddings trained on these corpora.
We create news article category classification datasets for 9 languages to evaluate the embeddings.
We evaluate the IndicNLP embeddings on multiple evaluation tasks. | @article{kunchukuttan2020indicnlpcorpus,
title={AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages},
author={Anoop Kunchukuttan and Divyanshu Kakwani and Satish Golla and Gokul N.C. and Avik Bhattacharyya and Mitesh M. Khapra and Pratyush Kumar},
year={2020},
journal={arXiv preprint arXiv:2005.00085},
} | 0 | 11 | 2022-06-20T07:38:55 | ## IndicNLP News Article Classification Dataset
We used the IndicNLP text corpora to create classification datasets comprising news articles and their categories for 9 languages. The dataset is balanced across classes. The following table contains the statistics of our dataset:
| Language | Classes | Articles per Class |
| --------- | ------------------------------------------- | ------------------ |
| Bengali | entertainment, sports | 7K |
| Gujarati | business, entertainment, sports | 680 |
| Kannada | entertainment, lifestyle, sports | 10K |
| Malayalam | business, entertainment, sports, technology | 1.5K |
| Marathi | entertainment, lifestyle, sports | 1.5K |
| Oriya | business, crime, entertainment, sports | 7.5K |
| Punjabi | business, entertainment, sports, politics | 780 |
| Tamil | entertainment, politics, sport | 3.9K |
| Telugu | entertainment, business, sports | 8K |
## Citing
If you are using any of the resources, please cite the following article:
```
@article{kunchukuttan2020indicnlpcorpus,
title={AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages},
author={Anoop Kunchukuttan and Divyanshu Kakwani and Satish Golla and Gokul N.C. and Avik Bhattacharyya and Mitesh M. Khapra and Pratyush Kumar},
year={2020},
journal={arXiv preprint arXiv:2005.00085},
}
```
| 1,626 | [
[
-0.01221466064453125,
-0.01149749755859375,
-0.00934600830078125,
0.0277557373046875,
-0.0237274169921875,
0.0268707275390625,
-0.0189208984375,
-0.03131103515625,
0.020263671875,
0.019683837890625,
-0.00518798828125,
-0.052398681640625,
-0.0418701171875,
0.... |
allenai/metaicl-data | 2022-06-30T21:18:49.000Z | [
"license:cc-by-nc-4.0",
"arxiv:2005.00700",
"region:us"
] | allenai | null | null | 1 | 11 | 2022-06-30T18:27:28 | ---
license: cc-by-nc-4.0
---
This is the downloaded and processed data from Meta's [MetaICL](https://github.com/facebookresearch/MetaICL).
We follow their ["How to Download and Preprocess"](https://github.com/facebookresearch/MetaICL#how-to-download-and-preprocess) instructions to obtain their modified versions of [CrossFit](https://github.com/INK-USC/CrossFit) and [UnifiedQA](https://arxiv.org/abs/2005.00700).
## Citation information
```
@inproceedings{ min2022metaicl,
title={ Meta{ICL}: Learning to Learn In Context },
author={ Min, Sewon and Lewis, Mike and Zettlemoyer, Luke and Hajishirzi, Hannaneh },
booktitle={ NAACL-HLT },
year={ 2022 }
}
@inproceedings{ ye2021crossfit,
title={ {C}ross{F}it: A Few-shot Learning Challenge for Cross-task Generalization in NLP },
author={ Ye, Qinyuan and Lin, Bill Yuchen and Ren, Xiang },
booktitle={ EMNLP },
year={ 2021 }
}
@inproceedings{ khashabi2020unifiedqa,
title={ {U}nified{QA}: Crossing Format Boundaries With a Single QA System },
author={ Khashabi, Daniel and Min, Sewon and Khot, Tushar and Sabharwal, Ashish and Tafjord, Oyvind and Clark, Peter and Hajishirzi, Hannaneh },
booktitle={ Findings of EMNLP },
year={ 2020 }
}
```
| 1,234 | [
[
-0.02435302734375,
-0.038482666015625,
0.0276947021484375,
0.015777587890625,
-0.00975799560546875,
0.00287628173828125,
-0.005466461181640625,
-0.03759765625,
0.033233642578125,
0.041900634765625,
-0.07318115234375,
-0.04302978515625,
-0.0208587646484375,
0... |
MicPie/unpredictable_cram-com | 2022-08-04T20:03:25.000Z | [
"task_categories:multiple-choice",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:text2text-generation",
"task_categories:table-question-answering",
"task_categories:text-generation",
"task_categories:text-classification",
"task_categories:tabular-cl... | MicPie | The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance. For more details please see the accompanying dataset card. | @misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
} | 0 | 11 | 2022-07-03T11:31:09 | ---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license:
- apache-2.0
multilinguality:
- monolingual
pretty_name: UnpredicTable-cram-com
size_categories:
- 100K<n<1M
source_datasets: []
task_categories:
- multiple-choice
- question-answering
- zero-shot-classification
- text2text-generation
- table-question-answering
- text-generation
- text-classification
- tabular-classification
task_ids:
- multiple-choice-qa
- extractive-qa
- open-domain-qa
- closed-domain-qa
- closed-book-qa
- open-book-qa
- language-modeling
- multi-class-classification
- natural-language-inference
- topic-classification
- multi-label-classification
- tabular-multi-class-classification
- tabular-multi-label-classification
---
# Dataset Card for "UnpredicTable-cram-com" - Dataset of Few-shot Tasks from Tables
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://ethanperez.net/unpredictable
- **Repository:** https://github.com/JunShern/few-shot-adaptation
- **Paper:** Few-shot Adaptation Works with UnpredicTable Data
- **Point of Contact:** junshern@nyu.edu, perez@nyu.edu
### Dataset Summary
The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance.
There are several dataset versions available:
* [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full): Starting from the initial WTC corpus of 50M tables, we apply our tables-to-tasks procedure to produce our resulting dataset, [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full), which comprises 413,299 tasks from 23,744 unique websites.
* [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique): This is the same as [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full) but filtered to have a maximum of one task per website. [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique) contains exactly 23,744 tasks from 23,744 websites.
* [UnpredicTable-5k](https://huggingface.co/datasets/MicPie/unpredictable_5k): This dataset contains 5k random tables from the full dataset.
* UnpredicTable data subsets based on a manual human quality rating (please see our publication for details of the ratings):
* [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low)
* [UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium)
* [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high)
* UnpredicTable data subsets based on the website of origin:
* [UnpredicTable-baseball-fantasysports-yahoo-com](https://huggingface.co/datasets/MicPie/unpredictable_baseball-fantasysports-yahoo-com)
* [UnpredicTable-bulbapedia-bulbagarden-net](https://huggingface.co/datasets/MicPie/unpredictable_bulbapedia-bulbagarden-net)
* [UnpredicTable-cappex-com](https://huggingface.co/datasets/MicPie/unpredictable_cappex-com)
* [UnpredicTable-cram-com](https://huggingface.co/datasets/MicPie/unpredictable_cram-com)
* [UnpredicTable-dividend-com](https://huggingface.co/datasets/MicPie/unpredictable_dividend-com)
* [UnpredicTable-dummies-com](https://huggingface.co/datasets/MicPie/unpredictable_dummies-com)
* [UnpredicTable-en-wikipedia-org](https://huggingface.co/datasets/MicPie/unpredictable_en-wikipedia-org)
* [UnpredicTable-ensembl-org](https://huggingface.co/datasets/MicPie/unpredictable_ensembl-org)
* [UnpredicTable-gamefaqs-com](https://huggingface.co/datasets/MicPie/unpredictable_gamefaqs-com)
* [UnpredicTable-mgoblog-com](https://huggingface.co/datasets/MicPie/unpredictable_mgoblog-com)
* [UnpredicTable-mmo-champion-com](https://huggingface.co/datasets/MicPie/unpredictable_mmo-champion-com)
* [UnpredicTable-msdn-microsoft-com](https://huggingface.co/datasets/MicPie/unpredictable_msdn-microsoft-com)
* [UnpredicTable-phonearena-com](https://huggingface.co/datasets/MicPie/unpredictable_phonearena-com)
* [UnpredicTable-sittercity-com](https://huggingface.co/datasets/MicPie/unpredictable_sittercity-com)
* [UnpredicTable-sporcle-com](https://huggingface.co/datasets/MicPie/unpredictable_sporcle-com)
* [UnpredicTable-studystack-com](https://huggingface.co/datasets/MicPie/unpredictable_studystack-com)
* [UnpredicTable-support-google-com](https://huggingface.co/datasets/MicPie/unpredictable_support-google-com)
* [UnpredicTable-w3-org](https://huggingface.co/datasets/MicPie/unpredictable_w3-org)
* [UnpredicTable-wiki-openmoko-org](https://huggingface.co/datasets/MicPie/unpredictable_wiki-openmoko-org)
* [UnpredicTable-wkdu-org](https://huggingface.co/datasets/MicPie/unpredictable_wkdu-org)
* UnpredicTable data subsets based on clustering (for the clustering details please see our publication):
* [UnpredicTable-cluster00](https://huggingface.co/datasets/MicPie/unpredictable_cluster00)
* [UnpredicTable-cluster01](https://huggingface.co/datasets/MicPie/unpredictable_cluster01)
* [UnpredicTable-cluster02](https://huggingface.co/datasets/MicPie/unpredictable_cluster02)
* [UnpredicTable-cluster03](https://huggingface.co/datasets/MicPie/unpredictable_cluster03)
* [UnpredicTable-cluster04](https://huggingface.co/datasets/MicPie/unpredictable_cluster04)
* [UnpredicTable-cluster05](https://huggingface.co/datasets/MicPie/unpredictable_cluster05)
* [UnpredicTable-cluster06](https://huggingface.co/datasets/MicPie/unpredictable_cluster06)
* [UnpredicTable-cluster07](https://huggingface.co/datasets/MicPie/unpredictable_cluster07)
* [UnpredicTable-cluster08](https://huggingface.co/datasets/MicPie/unpredictable_cluster08)
* [UnpredicTable-cluster09](https://huggingface.co/datasets/MicPie/unpredictable_cluster09)
* [UnpredicTable-cluster10](https://huggingface.co/datasets/MicPie/unpredictable_cluster10)
* [UnpredicTable-cluster11](https://huggingface.co/datasets/MicPie/unpredictable_cluster11)
* [UnpredicTable-cluster12](https://huggingface.co/datasets/MicPie/unpredictable_cluster12)
* [UnpredicTable-cluster13](https://huggingface.co/datasets/MicPie/unpredictable_cluster13)
* [UnpredicTable-cluster14](https://huggingface.co/datasets/MicPie/unpredictable_cluster14)
* [UnpredicTable-cluster15](https://huggingface.co/datasets/MicPie/unpredictable_cluster15)
* [UnpredicTable-cluster16](https://huggingface.co/datasets/MicPie/unpredictable_cluster16)
* [UnpredicTable-cluster17](https://huggingface.co/datasets/MicPie/unpredictable_cluster17)
* [UnpredicTable-cluster18](https://huggingface.co/datasets/MicPie/unpredictable_cluster18)
* [UnpredicTable-cluster19](https://huggingface.co/datasets/MicPie/unpredictable_cluster19)
* [UnpredicTable-cluster20](https://huggingface.co/datasets/MicPie/unpredictable_cluster20)
* [UnpredicTable-cluster21](https://huggingface.co/datasets/MicPie/unpredictable_cluster21)
* [UnpredicTable-cluster22](https://huggingface.co/datasets/MicPie/unpredictable_cluster22)
* [UnpredicTable-cluster23](https://huggingface.co/datasets/MicPie/unpredictable_cluster23)
* [UnpredicTable-cluster24](https://huggingface.co/datasets/MicPie/unpredictable_cluster24)
* [UnpredicTable-cluster25](https://huggingface.co/datasets/MicPie/unpredictable_cluster25)
* [UnpredicTable-cluster26](https://huggingface.co/datasets/MicPie/unpredictable_cluster26)
* [UnpredicTable-cluster27](https://huggingface.co/datasets/MicPie/unpredictable_cluster27)
* [UnpredicTable-cluster28](https://huggingface.co/datasets/MicPie/unpredictable_cluster28)
* [UnpredicTable-cluster29](https://huggingface.co/datasets/MicPie/unpredictable_cluster29)
* [UnpredicTable-cluster-noise](https://huggingface.co/datasets/MicPie/unpredictable_cluster-noise)
### Supported Tasks and Leaderboards
Since the tables come from the web, the distribution of tasks and topics is very broad. The shape of our dataset is very wide, i.e., we have 1000's of tasks, while each task has only a few examples, compared to most current NLP datasets which are very deep, i.e., 10s of tasks with many examples. This implies that our dataset covers a broad range of potential tasks, e.g., multiple-choice, question-answering, table-question-answering, text-classification, etc.
The intended use of this dataset is to improve few-shot performance by fine-tuning/pre-training on our dataset.
### Languages
English
## Dataset Structure
### Data Instances
Each task is represented as a jsonline file and consists of several few-shot examples. Each example is a dictionary containing a field 'task', which identifies the task, followed by an 'input', 'options', and 'output' field. The 'input' field contains several column elements of the same row in the table, while the 'output' field is a target which represents an individual column of the same row. Each task contains several such examples which can be concatenated as a few-shot task. In the case of multiple choice classification, the 'options' field contains the possible classes that a model needs to choose from.
There are also additional meta-data fields such as 'pageTitle', 'title', 'outputColName', 'url', 'wdcFile'.
### Data Fields
'task': task identifier
'input': column elements of a specific row in the table.
'options': for multiple choice classification, it provides the options to choose from.
'output': target column element of the same row as input.
'pageTitle': the title of the page containing the table.
'outputColName': output column name
'url': url to the website containing the table
'wdcFile': WDC Web Table Corpus file
### Data Splits
The UnpredicTable datasets do not come with additional data splits.
## Dataset Creation
### Curation Rationale
Few-shot training on multi-task datasets has been demonstrated to improve language models' few-shot learning (FSL) performance on new tasks, but it is unclear which training tasks lead to effective downstream task adaptation. Few-shot learning datasets are typically produced with expensive human curation, limiting the scale and diversity of the training tasks available to study. As an alternative source of few-shot data, we automatically extract 413,299 tasks from diverse internet tables. We provide this as a research resource to investigate the relationship between training data and few-shot learning.
### Source Data
#### Initial Data Collection and Normalization
We use internet tables from the English-language Relational Subset of the WDC Web Table Corpus 2015 (WTC). The WTC dataset tables were extracted from the July 2015 Common Crawl web corpus (http://webdatacommons.org/webtables/2015/EnglishStatistics.html). The dataset contains 50,820,165 tables from 323,160 web domains. We then convert the tables into few-shot learning tasks. Please see our publication for more details on the data collection and conversion pipeline.
#### Who are the source language producers?
The dataset is extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/).
### Annotations
#### Annotation process
Manual annotation was only carried out for the [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low),
[UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium), and [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high) data subsets to rate task quality. Detailed instructions of the annotation instructions can be found in our publication.
#### Who are the annotators?
Annotations were carried out by a lab assistant.
### Personal and Sensitive Information
The data was extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/), which in turn extracted tables from the [Common Crawl](https://commoncrawl.org/). We did not filter the data in any way. Thus any user identities or otherwise sensitive information (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history, etc.) might be contained in our dataset.
## Considerations for Using the Data
### Social Impact of Dataset
This dataset is intended for use as a research resource to investigate the relationship between training data and few-shot learning. As such, it contains high- and low-quality data, as well as diverse content that may be untruthful or inappropriate. Without careful investigation, it should not be used for training models that will be deployed for use in decision-critical or user-facing situations.
### Discussion of Biases
Since our dataset contains tables that are scraped from the web, it will also contain many toxic, racist, sexist, and otherwise harmful biases and texts. We have not run any analysis on the biases prevalent in our datasets. Neither have we explicitly filtered the content. This implies that a model trained on our dataset may potentially reflect harmful biases and toxic text that exist in our dataset.
### Other Known Limitations
No additional known limitations.
## Additional Information
### Dataset Curators
Jun Shern Chan, Michael Pieler, Jonathan Jao, Jérémy Scheurer, Ethan Perez
### Licensing Information
Apache 2.0
### Citation Information
```
@misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
}
```
| 14,795 | [
[
-0.03948974609375,
-0.040863037109375,
0.0307464599609375,
0.02435302734375,
0.005611419677734375,
0.0112457275390625,
-0.0112762451171875,
-0.042999267578125,
0.037200927734375,
0.021026611328125,
-0.07269287109375,
-0.046905517578125,
-0.047637939453125,
0... |
Yincen/SalienceEvaluation | 2022-07-04T02:36:58.000Z | [
"task_categories:text-classification",
"task_ids:multi-input-text-classification",
"annotations_creators:crowdsourced",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"source_datasets:original",
"language:zh",
"license:gpl-3.0",
"region:us"
] | Yincen | null | null | 1 | 11 | 2022-07-04T02:10:27 | ---
annotations_creators:
- crowdsourced
language:
- zh
language_creators:
- found
license:
- gpl-3.0
multilinguality:
- monolingual
pretty_name: Yincen/SalienceEvaluation
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- text-classification
task_ids:
- multi-input-text-classification
---
# Dataset Card for Yincen/SalienceEvaluation
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@github-username](https://github.com/qyccc) for adding this dataset. | 2,799 | [
[
-0.0210113525390625,
-0.0254974365234375,
0.01020050048828125,
0.022064208984375,
-0.0190582275390625,
0.001682281494140625,
-0.0250396728515625,
-0.0352783203125,
0.051544189453125,
0.033294677734375,
-0.067626953125,
-0.07525634765625,
-0.04193115234375,
0... |
MicPie/unpredictable_5k | 2022-08-04T19:36:03.000Z | [
"task_categories:multiple-choice",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:text2text-generation",
"task_categories:table-question-answering",
"task_categories:text-generation",
"task_categories:text-classification",
"task_categories:tabular-cl... | MicPie | The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance. For more details please see the accompanying dataset card. | @misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
} | 0 | 11 | 2022-07-06T18:51:40 | ---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license:
- apache-2.0
multilinguality:
- monolingual
pretty_name: UnpredicTable-5k
size_categories:
- 100K<n<1M
source_datasets: []
task_categories:
- multiple-choice
- question-answering
- zero-shot-classification
- text2text-generation
- table-question-answering
- text-generation
- text-classification
- tabular-classification
task_ids:
- multiple-choice-qa
- extractive-qa
- open-domain-qa
- closed-domain-qa
- closed-book-qa
- open-book-qa
- language-modeling
- multi-class-classification
- natural-language-inference
- topic-classification
- multi-label-classification
- tabular-multi-class-classification
- tabular-multi-label-classification
---
# Dataset Card for "UnpredicTable-5k" - Dataset of Few-shot Tasks from Tables
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://ethanperez.net/unpredictable
- **Repository:** https://github.com/JunShern/few-shot-adaptation
- **Paper:** Few-shot Adaptation Works with UnpredicTable Data
- **Point of Contact:** junshern@nyu.edu, perez@nyu.edu
### Dataset Summary
The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance.
There are several dataset versions available:
* [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full): Starting from the initial WTC corpus of 50M tables, we apply our tables-to-tasks procedure to produce our resulting dataset, [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full), which comprises 413,299 tasks from 23,744 unique websites.
* [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique): This is the same as [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full) but filtered to have a maximum of one task per website. [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique) contains exactly 23,744 tasks from 23,744 websites.
* [UnpredicTable-5k](https://huggingface.co/datasets/MicPie/unpredictable_5k): This dataset contains 5k random tables from the full dataset.
* UnpredicTable data subsets based on a manual human quality rating (please see our publication for details of the ratings):
* [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low)
* [UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium)
* [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high)
* UnpredicTable data subsets based on the website of origin:
* [UnpredicTable-baseball-fantasysports-yahoo-com](https://huggingface.co/datasets/MicPie/unpredictable_baseball-fantasysports-yahoo-com)
* [UnpredicTable-bulbapedia-bulbagarden-net](https://huggingface.co/datasets/MicPie/unpredictable_bulbapedia-bulbagarden-net)
* [UnpredicTable-cappex-com](https://huggingface.co/datasets/MicPie/unpredictable_cappex-com)
* [UnpredicTable-cram-com](https://huggingface.co/datasets/MicPie/unpredictable_cram-com)
* [UnpredicTable-dividend-com](https://huggingface.co/datasets/MicPie/unpredictable_dividend-com)
* [UnpredicTable-dummies-com](https://huggingface.co/datasets/MicPie/unpredictable_dummies-com)
* [UnpredicTable-en-wikipedia-org](https://huggingface.co/datasets/MicPie/unpredictable_en-wikipedia-org)
* [UnpredicTable-ensembl-org](https://huggingface.co/datasets/MicPie/unpredictable_ensembl-org)
* [UnpredicTable-gamefaqs-com](https://huggingface.co/datasets/MicPie/unpredictable_gamefaqs-com)
* [UnpredicTable-mgoblog-com](https://huggingface.co/datasets/MicPie/unpredictable_mgoblog-com)
* [UnpredicTable-mmo-champion-com](https://huggingface.co/datasets/MicPie/unpredictable_mmo-champion-com)
* [UnpredicTable-msdn-microsoft-com](https://huggingface.co/datasets/MicPie/unpredictable_msdn-microsoft-com)
* [UnpredicTable-phonearena-com](https://huggingface.co/datasets/MicPie/unpredictable_phonearena-com)
* [UnpredicTable-sittercity-com](https://huggingface.co/datasets/MicPie/unpredictable_sittercity-com)
* [UnpredicTable-sporcle-com](https://huggingface.co/datasets/MicPie/unpredictable_sporcle-com)
* [UnpredicTable-studystack-com](https://huggingface.co/datasets/MicPie/unpredictable_studystack-com)
* [UnpredicTable-support-google-com](https://huggingface.co/datasets/MicPie/unpredictable_support-google-com)
* [UnpredicTable-w3-org](https://huggingface.co/datasets/MicPie/unpredictable_w3-org)
* [UnpredicTable-wiki-openmoko-org](https://huggingface.co/datasets/MicPie/unpredictable_wiki-openmoko-org)
* [UnpredicTable-wkdu-org](https://huggingface.co/datasets/MicPie/unpredictable_wkdu-org)
* UnpredicTable data subsets based on clustering (for the clustering details please see our publication):
* [UnpredicTable-cluster00](https://huggingface.co/datasets/MicPie/unpredictable_cluster00)
* [UnpredicTable-cluster01](https://huggingface.co/datasets/MicPie/unpredictable_cluster01)
* [UnpredicTable-cluster02](https://huggingface.co/datasets/MicPie/unpredictable_cluster02)
* [UnpredicTable-cluster03](https://huggingface.co/datasets/MicPie/unpredictable_cluster03)
* [UnpredicTable-cluster04](https://huggingface.co/datasets/MicPie/unpredictable_cluster04)
* [UnpredicTable-cluster05](https://huggingface.co/datasets/MicPie/unpredictable_cluster05)
* [UnpredicTable-cluster06](https://huggingface.co/datasets/MicPie/unpredictable_cluster06)
* [UnpredicTable-cluster07](https://huggingface.co/datasets/MicPie/unpredictable_cluster07)
* [UnpredicTable-cluster08](https://huggingface.co/datasets/MicPie/unpredictable_cluster08)
* [UnpredicTable-cluster09](https://huggingface.co/datasets/MicPie/unpredictable_cluster09)
* [UnpredicTable-cluster10](https://huggingface.co/datasets/MicPie/unpredictable_cluster10)
* [UnpredicTable-cluster11](https://huggingface.co/datasets/MicPie/unpredictable_cluster11)
* [UnpredicTable-cluster12](https://huggingface.co/datasets/MicPie/unpredictable_cluster12)
* [UnpredicTable-cluster13](https://huggingface.co/datasets/MicPie/unpredictable_cluster13)
* [UnpredicTable-cluster14](https://huggingface.co/datasets/MicPie/unpredictable_cluster14)
* [UnpredicTable-cluster15](https://huggingface.co/datasets/MicPie/unpredictable_cluster15)
* [UnpredicTable-cluster16](https://huggingface.co/datasets/MicPie/unpredictable_cluster16)
* [UnpredicTable-cluster17](https://huggingface.co/datasets/MicPie/unpredictable_cluster17)
* [UnpredicTable-cluster18](https://huggingface.co/datasets/MicPie/unpredictable_cluster18)
* [UnpredicTable-cluster19](https://huggingface.co/datasets/MicPie/unpredictable_cluster19)
* [UnpredicTable-cluster20](https://huggingface.co/datasets/MicPie/unpredictable_cluster20)
* [UnpredicTable-cluster21](https://huggingface.co/datasets/MicPie/unpredictable_cluster21)
* [UnpredicTable-cluster22](https://huggingface.co/datasets/MicPie/unpredictable_cluster22)
* [UnpredicTable-cluster23](https://huggingface.co/datasets/MicPie/unpredictable_cluster23)
* [UnpredicTable-cluster24](https://huggingface.co/datasets/MicPie/unpredictable_cluster24)
* [UnpredicTable-cluster25](https://huggingface.co/datasets/MicPie/unpredictable_cluster25)
* [UnpredicTable-cluster26](https://huggingface.co/datasets/MicPie/unpredictable_cluster26)
* [UnpredicTable-cluster27](https://huggingface.co/datasets/MicPie/unpredictable_cluster27)
* [UnpredicTable-cluster28](https://huggingface.co/datasets/MicPie/unpredictable_cluster28)
* [UnpredicTable-cluster29](https://huggingface.co/datasets/MicPie/unpredictable_cluster29)
* [UnpredicTable-cluster-noise](https://huggingface.co/datasets/MicPie/unpredictable_cluster-noise)
### Supported Tasks and Leaderboards
Since the tables come from the web, the distribution of tasks and topics is very broad. The shape of our dataset is very wide, i.e., we have 1000's of tasks, while each task has only a few examples, compared to most current NLP datasets which are very deep, i.e., 10s of tasks with many examples. This implies that our dataset covers a broad range of potential tasks, e.g., multiple-choice, question-answering, table-question-answering, text-classification, etc.
The intended use of this dataset is to improve few-shot performance by fine-tuning/pre-training on our dataset.
### Languages
English
## Dataset Structure
### Data Instances
Each task is represented as a jsonline file and consists of several few-shot examples. Each example is a dictionary containing a field 'task', which identifies the task, followed by an 'input', 'options', and 'output' field. The 'input' field contains several column elements of the same row in the table, while the 'output' field is a target which represents an individual column of the same row. Each task contains several such examples which can be concatenated as a few-shot task. In the case of multiple choice classification, the 'options' field contains the possible classes that a model needs to choose from.
There are also additional meta-data fields such as 'pageTitle', 'title', 'outputColName', 'url', 'wdcFile'.
### Data Fields
'task': task identifier
'input': column elements of a specific row in the table.
'options': for multiple choice classification, it provides the options to choose from.
'output': target column element of the same row as input.
'pageTitle': the title of the page containing the table.
'outputColName': output column name
'url': url to the website containing the table
'wdcFile': WDC Web Table Corpus file
### Data Splits
The UnpredicTable datasets do not come with additional data splits.
## Dataset Creation
### Curation Rationale
Few-shot training on multi-task datasets has been demonstrated to improve language models' few-shot learning (FSL) performance on new tasks, but it is unclear which training tasks lead to effective downstream task adaptation. Few-shot learning datasets are typically produced with expensive human curation, limiting the scale and diversity of the training tasks available to study. As an alternative source of few-shot data, we automatically extract 413,299 tasks from diverse internet tables. We provide this as a research resource to investigate the relationship between training data and few-shot learning.
### Source Data
#### Initial Data Collection and Normalization
We use internet tables from the English-language Relational Subset of the WDC Web Table Corpus 2015 (WTC). The WTC dataset tables were extracted from the July 2015 Common Crawl web corpus (http://webdatacommons.org/webtables/2015/EnglishStatistics.html). The dataset contains 50,820,165 tables from 323,160 web domains. We then convert the tables into few-shot learning tasks. Please see our publication for more details on the data collection and conversion pipeline.
#### Who are the source language producers?
The dataset is extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/).
### Annotations
#### Annotation process
Manual annotation was only carried out for the [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low),
[UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium), and [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high) data subsets to rate task quality. Detailed instructions of the annotation instructions can be found in our publication.
#### Who are the annotators?
Annotations were carried out by a lab assistant.
### Personal and Sensitive Information
The data was extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/), which in turn extracted tables from the [Common Crawl](https://commoncrawl.org/). We did not filter the data in any way. Thus any user identities or otherwise sensitive information (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history, etc.) might be contained in our dataset.
## Considerations for Using the Data
### Social Impact of Dataset
This dataset is intended for use as a research resource to investigate the relationship between training data and few-shot learning. As such, it contains high- and low-quality data, as well as diverse content that may be untruthful or inappropriate. Without careful investigation, it should not be used for training models that will be deployed for use in decision-critical or user-facing situations.
### Discussion of Biases
Since our dataset contains tables that are scraped from the web, it will also contain many toxic, racist, sexist, and otherwise harmful biases and texts. We have not run any analysis on the biases prevalent in our datasets. Neither have we explicitly filtered the content. This implies that a model trained on our dataset may potentially reflect harmful biases and toxic text that exist in our dataset.
### Other Known Limitations
No additional known limitations.
## Additional Information
### Dataset Curators
Jun Shern Chan, Michael Pieler, Jonathan Jao, Jérémy Scheurer, Ethan Perez
### Licensing Information
Apache 2.0
### Citation Information
```
@misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
}
```
| 14,782 | [
[
-0.04052734375,
-0.038604736328125,
0.031707763671875,
0.02276611328125,
0.00579833984375,
0.0096588134765625,
-0.00806427001953125,
-0.045013427734375,
0.035919189453125,
0.0218963623046875,
-0.07275390625,
-0.047088623046875,
-0.04638671875,
0.016372680664... |
MicPie/unpredictable_unique | 2022-08-04T20:16:10.000Z | [
"task_categories:multiple-choice",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:text2text-generation",
"task_categories:table-question-answering",
"task_categories:text-generation",
"task_categories:text-classification",
"task_categories:tabular-cl... | MicPie | The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance. For more details please see the accompanying dataset card. | @misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
} | 0 | 11 | 2022-07-08T16:21:01 | ---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license:
- apache-2.0
multilinguality:
- monolingual
pretty_name: UnpredicTable-unique
size_categories:
- 100K<n<1M
source_datasets: []
task_categories:
- multiple-choice
- question-answering
- zero-shot-classification
- text2text-generation
- table-question-answering
- text-generation
- text-classification
- tabular-classification
task_ids:
- multiple-choice-qa
- extractive-qa
- open-domain-qa
- closed-domain-qa
- closed-book-qa
- open-book-qa
- language-modeling
- multi-class-classification
- natural-language-inference
- topic-classification
- multi-label-classification
- tabular-multi-class-classification
- tabular-multi-label-classification
---
# Dataset Card for "UnpredicTable-unique" - Dataset of Few-shot Tasks from Tables
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://ethanperez.net/unpredictable
- **Repository:** https://github.com/JunShern/few-shot-adaptation
- **Paper:** Few-shot Adaptation Works with UnpredicTable Data
- **Point of Contact:** junshern@nyu.edu, perez@nyu.edu
### Dataset Summary
The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance.
There are several dataset versions available:
* [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full): Starting from the initial WTC corpus of 50M tables, we apply our tables-to-tasks procedure to produce our resulting dataset, [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full), which comprises 413,299 tasks from 23,744 unique websites.
* [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique): This is the same as [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full) but filtered to have a maximum of one task per website. [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique) contains exactly 23,744 tasks from 23,744 websites.
* [UnpredicTable-5k](https://huggingface.co/datasets/MicPie/unpredictable_5k): This dataset contains 5k random tables from the full dataset.
* UnpredicTable data subsets based on a manual human quality rating (please see our publication for details of the ratings):
* [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low)
* [UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium)
* [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high)
* UnpredicTable data subsets based on the website of origin:
* [UnpredicTable-baseball-fantasysports-yahoo-com](https://huggingface.co/datasets/MicPie/unpredictable_baseball-fantasysports-yahoo-com)
* [UnpredicTable-bulbapedia-bulbagarden-net](https://huggingface.co/datasets/MicPie/unpredictable_bulbapedia-bulbagarden-net)
* [UnpredicTable-cappex-com](https://huggingface.co/datasets/MicPie/unpredictable_cappex-com)
* [UnpredicTable-cram-com](https://huggingface.co/datasets/MicPie/unpredictable_cram-com)
* [UnpredicTable-dividend-com](https://huggingface.co/datasets/MicPie/unpredictable_dividend-com)
* [UnpredicTable-dummies-com](https://huggingface.co/datasets/MicPie/unpredictable_dummies-com)
* [UnpredicTable-en-wikipedia-org](https://huggingface.co/datasets/MicPie/unpredictable_en-wikipedia-org)
* [UnpredicTable-ensembl-org](https://huggingface.co/datasets/MicPie/unpredictable_ensembl-org)
* [UnpredicTable-gamefaqs-com](https://huggingface.co/datasets/MicPie/unpredictable_gamefaqs-com)
* [UnpredicTable-mgoblog-com](https://huggingface.co/datasets/MicPie/unpredictable_mgoblog-com)
* [UnpredicTable-mmo-champion-com](https://huggingface.co/datasets/MicPie/unpredictable_mmo-champion-com)
* [UnpredicTable-msdn-microsoft-com](https://huggingface.co/datasets/MicPie/unpredictable_msdn-microsoft-com)
* [UnpredicTable-phonearena-com](https://huggingface.co/datasets/MicPie/unpredictable_phonearena-com)
* [UnpredicTable-sittercity-com](https://huggingface.co/datasets/MicPie/unpredictable_sittercity-com)
* [UnpredicTable-sporcle-com](https://huggingface.co/datasets/MicPie/unpredictable_sporcle-com)
* [UnpredicTable-studystack-com](https://huggingface.co/datasets/MicPie/unpredictable_studystack-com)
* [UnpredicTable-support-google-com](https://huggingface.co/datasets/MicPie/unpredictable_support-google-com)
* [UnpredicTable-w3-org](https://huggingface.co/datasets/MicPie/unpredictable_w3-org)
* [UnpredicTable-wiki-openmoko-org](https://huggingface.co/datasets/MicPie/unpredictable_wiki-openmoko-org)
* [UnpredicTable-wkdu-org](https://huggingface.co/datasets/MicPie/unpredictable_wkdu-org)
* UnpredicTable data subsets based on clustering (for the clustering details please see our publication):
* [UnpredicTable-cluster00](https://huggingface.co/datasets/MicPie/unpredictable_cluster00)
* [UnpredicTable-cluster01](https://huggingface.co/datasets/MicPie/unpredictable_cluster01)
* [UnpredicTable-cluster02](https://huggingface.co/datasets/MicPie/unpredictable_cluster02)
* [UnpredicTable-cluster03](https://huggingface.co/datasets/MicPie/unpredictable_cluster03)
* [UnpredicTable-cluster04](https://huggingface.co/datasets/MicPie/unpredictable_cluster04)
* [UnpredicTable-cluster05](https://huggingface.co/datasets/MicPie/unpredictable_cluster05)
* [UnpredicTable-cluster06](https://huggingface.co/datasets/MicPie/unpredictable_cluster06)
* [UnpredicTable-cluster07](https://huggingface.co/datasets/MicPie/unpredictable_cluster07)
* [UnpredicTable-cluster08](https://huggingface.co/datasets/MicPie/unpredictable_cluster08)
* [UnpredicTable-cluster09](https://huggingface.co/datasets/MicPie/unpredictable_cluster09)
* [UnpredicTable-cluster10](https://huggingface.co/datasets/MicPie/unpredictable_cluster10)
* [UnpredicTable-cluster11](https://huggingface.co/datasets/MicPie/unpredictable_cluster11)
* [UnpredicTable-cluster12](https://huggingface.co/datasets/MicPie/unpredictable_cluster12)
* [UnpredicTable-cluster13](https://huggingface.co/datasets/MicPie/unpredictable_cluster13)
* [UnpredicTable-cluster14](https://huggingface.co/datasets/MicPie/unpredictable_cluster14)
* [UnpredicTable-cluster15](https://huggingface.co/datasets/MicPie/unpredictable_cluster15)
* [UnpredicTable-cluster16](https://huggingface.co/datasets/MicPie/unpredictable_cluster16)
* [UnpredicTable-cluster17](https://huggingface.co/datasets/MicPie/unpredictable_cluster17)
* [UnpredicTable-cluster18](https://huggingface.co/datasets/MicPie/unpredictable_cluster18)
* [UnpredicTable-cluster19](https://huggingface.co/datasets/MicPie/unpredictable_cluster19)
* [UnpredicTable-cluster20](https://huggingface.co/datasets/MicPie/unpredictable_cluster20)
* [UnpredicTable-cluster21](https://huggingface.co/datasets/MicPie/unpredictable_cluster21)
* [UnpredicTable-cluster22](https://huggingface.co/datasets/MicPie/unpredictable_cluster22)
* [UnpredicTable-cluster23](https://huggingface.co/datasets/MicPie/unpredictable_cluster23)
* [UnpredicTable-cluster24](https://huggingface.co/datasets/MicPie/unpredictable_cluster24)
* [UnpredicTable-cluster25](https://huggingface.co/datasets/MicPie/unpredictable_cluster25)
* [UnpredicTable-cluster26](https://huggingface.co/datasets/MicPie/unpredictable_cluster26)
* [UnpredicTable-cluster27](https://huggingface.co/datasets/MicPie/unpredictable_cluster27)
* [UnpredicTable-cluster28](https://huggingface.co/datasets/MicPie/unpredictable_cluster28)
* [UnpredicTable-cluster29](https://huggingface.co/datasets/MicPie/unpredictable_cluster29)
* [UnpredicTable-cluster-noise](https://huggingface.co/datasets/MicPie/unpredictable_cluster-noise)
### Supported Tasks and Leaderboards
Since the tables come from the web, the distribution of tasks and topics is very broad. The shape of our dataset is very wide, i.e., we have 1000's of tasks, while each task has only a few examples, compared to most current NLP datasets which are very deep, i.e., 10s of tasks with many examples. This implies that our dataset covers a broad range of potential tasks, e.g., multiple-choice, question-answering, table-question-answering, text-classification, etc.
The intended use of this dataset is to improve few-shot performance by fine-tuning/pre-training on our dataset.
### Languages
English
## Dataset Structure
### Data Instances
Each task is represented as a jsonline file and consists of several few-shot examples. Each example is a dictionary containing a field 'task', which identifies the task, followed by an 'input', 'options', and 'output' field. The 'input' field contains several column elements of the same row in the table, while the 'output' field is a target which represents an individual column of the same row. Each task contains several such examples which can be concatenated as a few-shot task. In the case of multiple choice classification, the 'options' field contains the possible classes that a model needs to choose from.
There are also additional meta-data fields such as 'pageTitle', 'title', 'outputColName', 'url', 'wdcFile'.
### Data Fields
'task': task identifier
'input': column elements of a specific row in the table.
'options': for multiple choice classification, it provides the options to choose from.
'output': target column element of the same row as input.
'pageTitle': the title of the page containing the table.
'outputColName': output column name
'url': url to the website containing the table
'wdcFile': WDC Web Table Corpus file
### Data Splits
The UnpredicTable datasets do not come with additional data splits.
## Dataset Creation
### Curation Rationale
Few-shot training on multi-task datasets has been demonstrated to improve language models' few-shot learning (FSL) performance on new tasks, but it is unclear which training tasks lead to effective downstream task adaptation. Few-shot learning datasets are typically produced with expensive human curation, limiting the scale and diversity of the training tasks available to study. As an alternative source of few-shot data, we automatically extract 413,299 tasks from diverse internet tables. We provide this as a research resource to investigate the relationship between training data and few-shot learning.
### Source Data
#### Initial Data Collection and Normalization
We use internet tables from the English-language Relational Subset of the WDC Web Table Corpus 2015 (WTC). The WTC dataset tables were extracted from the July 2015 Common Crawl web corpus (http://webdatacommons.org/webtables/2015/EnglishStatistics.html). The dataset contains 50,820,165 tables from 323,160 web domains. We then convert the tables into few-shot learning tasks. Please see our publication for more details on the data collection and conversion pipeline.
#### Who are the source language producers?
The dataset is extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/).
### Annotations
#### Annotation process
Manual annotation was only carried out for the [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low),
[UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium), and [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high) data subsets to rate task quality. Detailed instructions of the annotation instructions can be found in our publication.
#### Who are the annotators?
Annotations were carried out by a lab assistant.
### Personal and Sensitive Information
The data was extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/), which in turn extracted tables from the [Common Crawl](https://commoncrawl.org/). We did not filter the data in any way. Thus any user identities or otherwise sensitive information (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history, etc.) might be contained in our dataset.
## Considerations for Using the Data
### Social Impact of Dataset
This dataset is intended for use as a research resource to investigate the relationship between training data and few-shot learning. As such, it contains high- and low-quality data, as well as diverse content that may be untruthful or inappropriate. Without careful investigation, it should not be used for training models that will be deployed for use in decision-critical or user-facing situations.
### Discussion of Biases
Since our dataset contains tables that are scraped from the web, it will also contain many toxic, racist, sexist, and otherwise harmful biases and texts. We have not run any analysis on the biases prevalent in our datasets. Neither have we explicitly filtered the content. This implies that a model trained on our dataset may potentially reflect harmful biases and toxic text that exist in our dataset.
### Other Known Limitations
No additional known limitations.
## Additional Information
### Dataset Curators
Jun Shern Chan, Michael Pieler, Jonathan Jao, Jérémy Scheurer, Ethan Perez
### Licensing Information
Apache 2.0
### Citation Information
```
@misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
}
```
| 14,791 | [
[
-0.039459228515625,
-0.040008544921875,
0.0311431884765625,
0.0241851806640625,
0.0052490234375,
0.0111083984375,
-0.00867462158203125,
-0.043182373046875,
0.03759765625,
0.0222930908203125,
-0.07318115234375,
-0.047760009765625,
-0.046112060546875,
0.015472... |
MicPie/unpredictable_cluster25 | 2022-08-04T20:00:11.000Z | [
"task_categories:multiple-choice",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:text2text-generation",
"task_categories:table-question-answering",
"task_categories:text-generation",
"task_categories:text-classification",
"task_categories:tabular-cl... | MicPie | The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance. For more details please see the accompanying dataset card. | @misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
} | 0 | 11 | 2022-07-08T18:35:02 | ---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license:
- apache-2.0
multilinguality:
- monolingual
pretty_name: UnpredicTable-cluster25
size_categories:
- 100K<n<1M
source_datasets: []
task_categories:
- multiple-choice
- question-answering
- zero-shot-classification
- text2text-generation
- table-question-answering
- text-generation
- text-classification
- tabular-classification
task_ids:
- multiple-choice-qa
- extractive-qa
- open-domain-qa
- closed-domain-qa
- closed-book-qa
- open-book-qa
- language-modeling
- multi-class-classification
- natural-language-inference
- topic-classification
- multi-label-classification
- tabular-multi-class-classification
- tabular-multi-label-classification
---
# Dataset Card for "UnpredicTable-cluster25" - Dataset of Few-shot Tasks from Tables
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://ethanperez.net/unpredictable
- **Repository:** https://github.com/JunShern/few-shot-adaptation
- **Paper:** Few-shot Adaptation Works with UnpredicTable Data
- **Point of Contact:** junshern@nyu.edu, perez@nyu.edu
### Dataset Summary
The UnpredicTable dataset consists of web tables formatted as few-shot tasks for fine-tuning language models to improve their few-shot performance.
There are several dataset versions available:
* [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full): Starting from the initial WTC corpus of 50M tables, we apply our tables-to-tasks procedure to produce our resulting dataset, [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full), which comprises 413,299 tasks from 23,744 unique websites.
* [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique): This is the same as [UnpredicTable-full](https://huggingface.co/datasets/MicPie/unpredictable_full) but filtered to have a maximum of one task per website. [UnpredicTable-unique](https://huggingface.co/datasets/MicPie/unpredictable_unique) contains exactly 23,744 tasks from 23,744 websites.
* [UnpredicTable-5k](https://huggingface.co/datasets/MicPie/unpredictable_5k): This dataset contains 5k random tables from the full dataset.
* UnpredicTable data subsets based on a manual human quality rating (please see our publication for details of the ratings):
* [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low)
* [UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium)
* [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high)
* UnpredicTable data subsets based on the website of origin:
* [UnpredicTable-baseball-fantasysports-yahoo-com](https://huggingface.co/datasets/MicPie/unpredictable_baseball-fantasysports-yahoo-com)
* [UnpredicTable-bulbapedia-bulbagarden-net](https://huggingface.co/datasets/MicPie/unpredictable_bulbapedia-bulbagarden-net)
* [UnpredicTable-cappex-com](https://huggingface.co/datasets/MicPie/unpredictable_cappex-com)
* [UnpredicTable-cram-com](https://huggingface.co/datasets/MicPie/unpredictable_cram-com)
* [UnpredicTable-dividend-com](https://huggingface.co/datasets/MicPie/unpredictable_dividend-com)
* [UnpredicTable-dummies-com](https://huggingface.co/datasets/MicPie/unpredictable_dummies-com)
* [UnpredicTable-en-wikipedia-org](https://huggingface.co/datasets/MicPie/unpredictable_en-wikipedia-org)
* [UnpredicTable-ensembl-org](https://huggingface.co/datasets/MicPie/unpredictable_ensembl-org)
* [UnpredicTable-gamefaqs-com](https://huggingface.co/datasets/MicPie/unpredictable_gamefaqs-com)
* [UnpredicTable-mgoblog-com](https://huggingface.co/datasets/MicPie/unpredictable_mgoblog-com)
* [UnpredicTable-mmo-champion-com](https://huggingface.co/datasets/MicPie/unpredictable_mmo-champion-com)
* [UnpredicTable-msdn-microsoft-com](https://huggingface.co/datasets/MicPie/unpredictable_msdn-microsoft-com)
* [UnpredicTable-phonearena-com](https://huggingface.co/datasets/MicPie/unpredictable_phonearena-com)
* [UnpredicTable-sittercity-com](https://huggingface.co/datasets/MicPie/unpredictable_sittercity-com)
* [UnpredicTable-sporcle-com](https://huggingface.co/datasets/MicPie/unpredictable_sporcle-com)
* [UnpredicTable-studystack-com](https://huggingface.co/datasets/MicPie/unpredictable_studystack-com)
* [UnpredicTable-support-google-com](https://huggingface.co/datasets/MicPie/unpredictable_support-google-com)
* [UnpredicTable-w3-org](https://huggingface.co/datasets/MicPie/unpredictable_w3-org)
* [UnpredicTable-wiki-openmoko-org](https://huggingface.co/datasets/MicPie/unpredictable_wiki-openmoko-org)
* [UnpredicTable-wkdu-org](https://huggingface.co/datasets/MicPie/unpredictable_wkdu-org)
* UnpredicTable data subsets based on clustering (for the clustering details please see our publication):
* [UnpredicTable-cluster00](https://huggingface.co/datasets/MicPie/unpredictable_cluster00)
* [UnpredicTable-cluster01](https://huggingface.co/datasets/MicPie/unpredictable_cluster01)
* [UnpredicTable-cluster02](https://huggingface.co/datasets/MicPie/unpredictable_cluster02)
* [UnpredicTable-cluster03](https://huggingface.co/datasets/MicPie/unpredictable_cluster03)
* [UnpredicTable-cluster04](https://huggingface.co/datasets/MicPie/unpredictable_cluster04)
* [UnpredicTable-cluster05](https://huggingface.co/datasets/MicPie/unpredictable_cluster05)
* [UnpredicTable-cluster06](https://huggingface.co/datasets/MicPie/unpredictable_cluster06)
* [UnpredicTable-cluster07](https://huggingface.co/datasets/MicPie/unpredictable_cluster07)
* [UnpredicTable-cluster08](https://huggingface.co/datasets/MicPie/unpredictable_cluster08)
* [UnpredicTable-cluster09](https://huggingface.co/datasets/MicPie/unpredictable_cluster09)
* [UnpredicTable-cluster10](https://huggingface.co/datasets/MicPie/unpredictable_cluster10)
* [UnpredicTable-cluster11](https://huggingface.co/datasets/MicPie/unpredictable_cluster11)
* [UnpredicTable-cluster12](https://huggingface.co/datasets/MicPie/unpredictable_cluster12)
* [UnpredicTable-cluster13](https://huggingface.co/datasets/MicPie/unpredictable_cluster13)
* [UnpredicTable-cluster14](https://huggingface.co/datasets/MicPie/unpredictable_cluster14)
* [UnpredicTable-cluster15](https://huggingface.co/datasets/MicPie/unpredictable_cluster15)
* [UnpredicTable-cluster16](https://huggingface.co/datasets/MicPie/unpredictable_cluster16)
* [UnpredicTable-cluster17](https://huggingface.co/datasets/MicPie/unpredictable_cluster17)
* [UnpredicTable-cluster18](https://huggingface.co/datasets/MicPie/unpredictable_cluster18)
* [UnpredicTable-cluster19](https://huggingface.co/datasets/MicPie/unpredictable_cluster19)
* [UnpredicTable-cluster20](https://huggingface.co/datasets/MicPie/unpredictable_cluster20)
* [UnpredicTable-cluster21](https://huggingface.co/datasets/MicPie/unpredictable_cluster21)
* [UnpredicTable-cluster22](https://huggingface.co/datasets/MicPie/unpredictable_cluster22)
* [UnpredicTable-cluster23](https://huggingface.co/datasets/MicPie/unpredictable_cluster23)
* [UnpredicTable-cluster24](https://huggingface.co/datasets/MicPie/unpredictable_cluster24)
* [UnpredicTable-cluster25](https://huggingface.co/datasets/MicPie/unpredictable_cluster25)
* [UnpredicTable-cluster26](https://huggingface.co/datasets/MicPie/unpredictable_cluster26)
* [UnpredicTable-cluster27](https://huggingface.co/datasets/MicPie/unpredictable_cluster27)
* [UnpredicTable-cluster28](https://huggingface.co/datasets/MicPie/unpredictable_cluster28)
* [UnpredicTable-cluster29](https://huggingface.co/datasets/MicPie/unpredictable_cluster29)
* [UnpredicTable-cluster-noise](https://huggingface.co/datasets/MicPie/unpredictable_cluster-noise)
### Supported Tasks and Leaderboards
Since the tables come from the web, the distribution of tasks and topics is very broad. The shape of our dataset is very wide, i.e., we have 1000's of tasks, while each task has only a few examples, compared to most current NLP datasets which are very deep, i.e., 10s of tasks with many examples. This implies that our dataset covers a broad range of potential tasks, e.g., multiple-choice, question-answering, table-question-answering, text-classification, etc.
The intended use of this dataset is to improve few-shot performance by fine-tuning/pre-training on our dataset.
### Languages
English
## Dataset Structure
### Data Instances
Each task is represented as a jsonline file and consists of several few-shot examples. Each example is a dictionary containing a field 'task', which identifies the task, followed by an 'input', 'options', and 'output' field. The 'input' field contains several column elements of the same row in the table, while the 'output' field is a target which represents an individual column of the same row. Each task contains several such examples which can be concatenated as a few-shot task. In the case of multiple choice classification, the 'options' field contains the possible classes that a model needs to choose from.
There are also additional meta-data fields such as 'pageTitle', 'title', 'outputColName', 'url', 'wdcFile'.
### Data Fields
'task': task identifier
'input': column elements of a specific row in the table.
'options': for multiple choice classification, it provides the options to choose from.
'output': target column element of the same row as input.
'pageTitle': the title of the page containing the table.
'outputColName': output column name
'url': url to the website containing the table
'wdcFile': WDC Web Table Corpus file
### Data Splits
The UnpredicTable datasets do not come with additional data splits.
## Dataset Creation
### Curation Rationale
Few-shot training on multi-task datasets has been demonstrated to improve language models' few-shot learning (FSL) performance on new tasks, but it is unclear which training tasks lead to effective downstream task adaptation. Few-shot learning datasets are typically produced with expensive human curation, limiting the scale and diversity of the training tasks available to study. As an alternative source of few-shot data, we automatically extract 413,299 tasks from diverse internet tables. We provide this as a research resource to investigate the relationship between training data and few-shot learning.
### Source Data
#### Initial Data Collection and Normalization
We use internet tables from the English-language Relational Subset of the WDC Web Table Corpus 2015 (WTC). The WTC dataset tables were extracted from the July 2015 Common Crawl web corpus (http://webdatacommons.org/webtables/2015/EnglishStatistics.html). The dataset contains 50,820,165 tables from 323,160 web domains. We then convert the tables into few-shot learning tasks. Please see our publication for more details on the data collection and conversion pipeline.
#### Who are the source language producers?
The dataset is extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/).
### Annotations
#### Annotation process
Manual annotation was only carried out for the [UnpredicTable-rated-low](https://huggingface.co/datasets/MicPie/unpredictable_rated-low),
[UnpredicTable-rated-medium](https://huggingface.co/datasets/MicPie/unpredictable_rated-medium), and [UnpredicTable-rated-high](https://huggingface.co/datasets/MicPie/unpredictable_rated-high) data subsets to rate task quality. Detailed instructions of the annotation instructions can be found in our publication.
#### Who are the annotators?
Annotations were carried out by a lab assistant.
### Personal and Sensitive Information
The data was extracted from [WDC Web Table Corpora](http://webdatacommons.org/webtables/), which in turn extracted tables from the [Common Crawl](https://commoncrawl.org/). We did not filter the data in any way. Thus any user identities or otherwise sensitive information (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history, etc.) might be contained in our dataset.
## Considerations for Using the Data
### Social Impact of Dataset
This dataset is intended for use as a research resource to investigate the relationship between training data and few-shot learning. As such, it contains high- and low-quality data, as well as diverse content that may be untruthful or inappropriate. Without careful investigation, it should not be used for training models that will be deployed for use in decision-critical or user-facing situations.
### Discussion of Biases
Since our dataset contains tables that are scraped from the web, it will also contain many toxic, racist, sexist, and otherwise harmful biases and texts. We have not run any analysis on the biases prevalent in our datasets. Neither have we explicitly filtered the content. This implies that a model trained on our dataset may potentially reflect harmful biases and toxic text that exist in our dataset.
### Other Known Limitations
No additional known limitations.
## Additional Information
### Dataset Curators
Jun Shern Chan, Michael Pieler, Jonathan Jao, Jérémy Scheurer, Ethan Perez
### Licensing Information
Apache 2.0
### Citation Information
```
@misc{chan2022few,
author = {Chan, Jun Shern and Pieler, Michael and Jao, Jonathan and Scheurer, Jérémy and Perez, Ethan},
title = {Few-shot Adaptation Works with UnpredicTable Data},
publisher={arXiv},
year = {2022},
url = {https://arxiv.org/abs/2208.01009}
}
```
| 14,797 | [
[
-0.04144287109375,
-0.04022216796875,
0.032958984375,
0.0238800048828125,
0.006443023681640625,
0.01129150390625,
-0.0110321044921875,
-0.0421142578125,
0.037139892578125,
0.0205535888671875,
-0.0733642578125,
-0.049224853515625,
-0.045806884765625,
0.012931... |
Heriot-WattUniversity/dialog_babi | 2022-07-12T08:27:12.000Z | [
"arxiv:1605.07683",
"arxiv:1502.05698",
"region:us"
] | Heriot-WattUniversity | This section presents the set of 6 tasks for testing end-to-end dialog systems in the restaurant domain described in the paper:
Antoine Bordes, Y-Lan Boureau, Jason Weston, Learning End-to-End Goal-Oriented Dialog, arxiv:1605.07683.
Each task tests a unique aspect of dialog. Tasks are designed to complement the set of 20 bAbI tasks for story understanding of the previous section.
For each task, there are 1000 dialogs for training, 1000 for development and 1000 for testing. For tasks 1-5, we also include a second test set (with suffix -OOV.txt) that contains dialogs including entities not present in training and development sets. | @article{bordes2016learning,
title={Learning end-to-end goal-oriented dialog},
author={Bordes, Antoine and Boureau, Y-Lan and Weston, Jason},
journal={arXiv preprint arXiv:1605.07683},
year={2016}
} | 1 | 11 | 2022-07-09T09:32:32 | # Dialog bAbI tasks data
In this directory is the set of 6 tasks for testing end-to-end dialog systems in the restaurant domain as described in the paper "Learning End-to-End Goal-Oriented Dialog" by Bordes & Weston (http://arxiv.org/abs/1605.07683). The aim is that each task tests a unique aspect of dialog. Tasks are designed to complement the set of 20 bAbI tasks for story understanding already released with the paper "Towards AI Complete Question Answering: A Set of Prerequisite Toy Tasks" by Weston et al. (http://arxiv.org/abs/1502.05698).
## Data
For each task, there are 1000 dialogs for training, 1000 for development and 1000 for testing. For tasks 1-5, we also include a second test set (with suffix -OOV.txt) that contains dialogs including entities not present in training and development sets.
The file format for each task is as follows:
`ID user_utterance [tab] bot_utterances`
The IDs for a given dialog start at 1 and increase. When the IDs in a file reset back to 1 you can consider the following sentences as a new dialog. When the bot speaks two times in a row, we used the special token "<SILENCE>" to fill in for the missing user utterance.
For example (for task 1):
```
1 hi hello what can i help you with today
2 can you make a restaurant reservation with italian cuisine for six people in a cheap price range i'm on it
3 <SILENCE> where should it be
4 rome please ok let me look into some options for you
5 <SILENCE> api_call italian rome six cheap
```
The goal of the tasks is to predict the bot utterances, that can be sentences or API calls (sentences starting with the special token "api_call").
Along with the train, dev and test sets, we also include a knowledge base file (dialog-babi-kb-all.txt) that contain all entities appearing in dialogs for tasks 1-5. We also include a file containing the candidates to select the answer from (dialog-babi-candidates.txt) for tasks 1-5, that is simply made of all the bot utterances in train, dev, test for these tasks.
Task 6 is a bit different since its data comes from the Dialog State Tracking Challenge 2 (http://camdial.org/~mh521/dstc/), which we modified to convert it into the same format as the other tasks. There is no OOV test set associated with this task and the knowledge base (dialog-babi-task6-dstc2-kb.txt) is imperfect. This task has its own candidates file (dialog-babi-task6-dstc2-candidates.txt).
## License
This dataset is released under Creative Commons Attribution 3.0 Unported license. A copy of this license is included with the data.
## Contact
The author of this porting is Alessandro Suglia and he has only made available the dataset via
Huggingface datasets.
For more details on the dataset and baselines, see the paper "Learning End-to-End Goal-Oriented Dialog" by Antoine Bordes and Jason Weston (http://arxiv.org/abs/1605.07683). For any information, contact Antoine Bordes : abordes (at) fb (dot) com .
| 2,929 | [
[
-0.0210418701171875,
-0.07598876953125,
0.0216064453125,
-0.00609588623046875,
0.00531005859375,
0.0028667449951171875,
-0.0013952255249023438,
-0.02923583984375,
-0.007007598876953125,
0.054534912109375,
-0.0689697265625,
-0.0341796875,
-0.0211944580078125,
... |
RaphaelOlivier/librispeech_asr_adversarial | 2022-08-03T00:02:08.000Z | [
"region:us"
] | RaphaelOlivier | LibriSpeech is a corpus of approximately 1000 hours of read English speech with sampling rate of 16 kHz,
prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read
audiobooks from the LibriVox project, and has been carefully segmented and aligned.
Note that in order to limit the required storage for preparing this dataset, the audio
is stored in the .flac format and is not converted to a float32 array. To convert, the audio
file to a float32 array, please make use of the `.map()` function as follows:
```python
import soundfile as sf
def map_to_array(batch):
speech_array, _ = sf.read(batch["file"])
batch["speech"] = speech_array
return batch
dataset = dataset.map(map_to_array, remove_columns=["file"])
``` | @inproceedings{panayotov2015librispeech,
title={Librispeech: an ASR corpus based on public domain audio books},
author={Panayotov, Vassil and Chen,
Guoguo and Povey, Daniel and Khudanpur, Sanjeev},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on},
pages={5206--5210},
year={2015},
organization={IEEE}
} | 0 | 11 | 2022-07-18T19:08:15 | # Description
This dataset is a subset of [https://huggingface.co/datasets/librispeech_asr](LibriSpeech) that has been adversarially modified. It is designed to fool ASR models into predicting a target of our choosing instead of the correct output.
## Splits
The dataset contains several splits. Each split consists of the same utterances, modified with different types and amount of noise. 3 noises have been used:
* Adversarial noise of radius 0.04 (`adv_0.04` split)
* Adversarial noise of radius 0.015 (`adv_0.015` split)
* Adversarial noise of radius 0.015 combined with Room Impulse Response (RIR) noise (`adv_0.015_RIR` split)
In addition we provide the original inputs (`natural` split)
For each split we actually provide two text keys: `true_text` which is the original LibriSpeech label, i.e. the sentence one can actually hear when listening to the audio; and `target_text`, which is the target sentence of our adversarial attack. An ASR model that this dataset fools would get a low WER on `target_text` and a high WER on `true_text`. An ASR model robust to this dataset would get the opposite.
## Usage
You should evaluate your model on this dataset as you would evaluate it on LibriSpeech. Here is an example with Wav2Vec2
```python
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
from jiwer import wer
librispeech_adv_eval = load_dataset("RaphaelOlivier/librispeech_asr_adversarial", "adv", split="adv_0.15_adv_txt")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
def map_to_pred(batch):
input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values
with torch.no_grad():
logits = model(input_values.to("cuda")).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
batch["transcription"] = transcription
return batch
result = librispeech_adv_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["audio"])
print("WER on correct labels:", wer(result["true_text"], result["transcription"]))
print("WER on attack targets:", wer(result["target_text"], result["transcription"]))
```
*Result (WER)*:
| "0.015 target_text" | "0.015 true_text" | "0.04 target_text" | "0.04 true_text"
|---|---|---|---|
| 58.2 | 108 | 49.5 | 108 |
| 2,464 | [
[
-0.01873779296875,
-0.05621337890625,
0.00817108154296875,
-0.0003414154052734375,
-0.007297515869140625,
-0.01055908203125,
-0.02783203125,
-0.0279693603515625,
0.00971221923828125,
0.039031982421875,
-0.048797607421875,
-0.040313720703125,
-0.053985595703125,
... |
OATML-Markslab/ProteinGym | 2022-07-29T00:12:02.000Z | [
"arxiv:2205.13760",
"region:us"
] | OATML-Markslab | null | null | 7 | 11 | 2022-07-28T22:55:30 | ## ProteinGym benchmarks overview
ProteinGym is an extensive set of Deep Mutational Scanning (DMS) assays curated to enable thorough comparisons of various mutation effect predictors indifferent regimes. It is comprised of two benchmarks: 1) a substitution benchmark which consists of the experimental characterisation of ∼1.5M missense variants across 87 DMS assays 2) an indel benchmark that includes ∼300k mutants across 7 DMS assays.
Each processed file in each benchmark corresponds to a single DMS assay, and contains the following three variables:
1) mutant (str):
- for the substitution benchmark, it describes the set of substitutions to apply on the reference sequence to obtain the mutated sequence (eg., A1P:D2N implies the amino acid 'A' at position 1 should be replaced by 'P', and 'D' at position 2 should be replaced by 'N')
- for the indel benchmark, it corresponds to the full mutated sequence
2) DMS_score (float): corresponds to the experimental measurement in the DMS assay. Across all assays, the higher the DMS_score value, the higher the fitness of the mutated protein
3) DMS_score_bin (int): indicates whether the DMS_score is above the fitness cutoff (1 is fit, 0 is not fit)
Additionally, we provide two reference files (ProteinGym_reference_file_substitutions.csv and ProteinGym_reference_file_indels.csv) that give further details on each assay and contain in particular:
- The UniProt_ID of the corresponding protein, along with taxon and MSA depth category
- The target sequence (target_seq) used in the assay
- Details on how the DMS_score was created from the raw files and how it was binarized
## Reference
If you use ProteinGym in your work, please cite the following paper:
```
Notin, P., Dias, M., Frazer, J., Marchena-Hurtado, J., Gomez, A., Marks, D.S., Gal, Y. (2022). Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval. ICML.
```
## Links
- Pre-print: https://arxiv.org/abs/2205.13760
- Code: https://github.com/OATML-Markslab/Tranception | 2,036 | [
[
-0.03387451171875,
-0.036895751953125,
0.023681640625,
-0.00032830238342285156,
-0.011962890625,
0.01349639892578125,
0.021820068359375,
-0.01444244384765625,
0.021881103515625,
0.030548095703125,
-0.050933837890625,
-0.04754638671875,
-0.056915283203125,
0.... |
AI-Growth-Lab/patents_claims_1.5m_traim_test | 2022-07-31T20:48:51.000Z | [
"region:us"
] | AI-Growth-Lab | null | null | 1 | 11 | 2022-07-31T20:01:19 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Yaxin/SemEval2014Task4NLTK | 2022-08-15T06:56:51.000Z | [
"region:us"
] | Yaxin | A collection of SemEval2014 specifically designed to aid research in Aspect Based Sentiment Analysis. | @article{2014SemEval,
title={SemEval-2014 Task 4: Aspect Based Sentiment Analysis},
author={ Pontiki, M. and D Galanis and Pavlopoulos, J. and Papageorgiou, H. and Manandhar, S. },
journal={Proceedings of International Workshop on Semantic Evaluation at},
year={2014},
} | 0 | 11 | 2022-08-15T06:53:38 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
EMBO/sd-character-level-ner | 2022-10-23T06:41:24.000Z | [
"task_categories:text-classification",
"task_ids:multi-class-classification",
"task_ids:named-entity-recognition",
"task_ids:parsing",
"annotations_creators:expert-generated",
"language_creators:expert-generated",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"language:en",
"license... | EMBO | This dataset is based on the SourceData database and is intented to facilitate training of NLP tasks in the cell and molecualr biology domain. | @Unpublished{
huggingface: dataset,
title = {SourceData NLP},
authors={Thomas Lemberger & Jorge Abreu-Vicente, EMBO},
year={2021}
} | 0 | 11 | 2022-09-22T13:57:31 | ---
annotations_creators:
- expert-generated
language_creators:
- expert-generated
language:
- en
license:
- cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets: []
task_categories:
- text-classification
- structure-prediction
task_ids:
- multi-class-classification
- named-entity-recognition
- parsing
---
# Dataset Card for sd-nlp
## Table of Contents
- [Dataset Card for [EMBO/sd-nlp-non-tokenized]](#dataset-card-for-dataset-name)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://sourcedata.embo.org
- **Repository:** https://github.com/source-data/soda-roberta
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** thomas.lemberger@embo.org, jorge.abreu@embo.org
### Dataset Summary
This dataset is based on the content of the SourceData (https://sourcedata.embo.org) database, which contains manually annotated figure legends written in English and extracted from scientific papers in the domain of cell and molecular biology (Liechti et al, Nature Methods, 2017, https://doi.org/10.1038/nmeth.4471).
Unlike the dataset [`sd-nlp`](https://huggingface.co/datasets/EMBO/sd-nlp), pre-tokenized with the `roberta-base` tokenizer, this dataset is not previously tokenized, but just splitted into words. Users can therefore use it to fine-tune other models.
Additional details at https://github.com/source-data/soda-roberta
### Supported Tasks and Leaderboards
Tags are provided as [IOB2-style tags](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)).
`PANELIZATION`: figure captions (or figure legends) are usually composed of segments that each refer to one of several 'panels' of the full figure. Panels tend to represent results obtained with a coherent method and depicts data points that can be meaningfully compared to each other. `PANELIZATION` provide the start (B-PANEL_START) of these segments and allow to train for recogntion of the boundary between consecutive panel lengends.
`NER`: biological and chemical entities are labeled. Specifically the following entities are tagged:
- `SMALL_MOLECULE`: small molecules
- `GENEPROD`: gene products (genes and proteins)
- `SUBCELLULAR`: subcellular components
- `CELL`: cell types and cell lines.
- `TISSUE`: tissues and organs
- `ORGANISM`: species
- `EXP_ASSAY`: experimental assays
`ROLES`: the role of entities with regard to the causal hypotheses tested in the reported results. The tags are:
- `CONTROLLED_VAR`: entities that are associated with experimental variables and that subjected to controlled and targeted perturbations.
- `MEASURED_VAR`: entities that are associated with the variables measured and the object of the measurements.
`BORING`: entities are marked with the tag `BORING` when they are more of descriptive value and not directly associated with causal hypotheses ('boring' is not an ideal choice of word, but it is short...). Typically, these entities are so-called 'reporter' geneproducts, entities used as common baseline across samples, or specify the context of the experiment (cellular system, species, etc...).
### Languages
The text in the dataset is English.
## Dataset Structure
### Data Instances
```json
{'text': '(E) Quantification of the number of cells without γ-Tubulin at centrosomes (γ-Tub -) in pachytene and diplotene spermatocytes in control, Plk1(∆/∆) and BI2536-treated spermatocytes. Data represent average of two biological replicates per condition. ',
'labels': [0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
13,
14,
14,
14,
14,
14,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
3,
4,
4,
4,
4,
4,
4,
4,
4,
0,
0,
0,
0,
5,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
0,
0,
3,
4,
4,
4,
4,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
7,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
3,
4,
4,
4,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
1,
2,
2,
2,
2,
2,
0,
0,
0,
0,
0,
0,
0,
0,
0,
7,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0]}
```
### Data Fields
- `text`: `str` of the text
- `label_ids` dictionary composed of list of strings on a character-level:
- `entity_types`: `list` of `strings` for the IOB2 tags for entity type; possible value in `["O", "I-SMALL_MOLECULE", "B-SMALL_MOLECULE", "I-GENEPROD", "B-GENEPROD", "I-SUBCELLULAR", "B-SUBCELLULAR", "I-CELL", "B-CELL", "I-TISSUE", "B-TISSUE", "I-ORGANISM", "B-ORGANISM", "I-EXP_ASSAY", "B-EXP_ASSAY"]`
- `panel_start`: `list` of `strings` for IOB2 tags `["O", "B-PANEL_START"]`
### Data Splits
```python
DatasetDict({
train: Dataset({
features: ['text', 'labels'],
num_rows: 66085
})
test: Dataset({
features: ['text', 'labels'],
num_rows: 8225
})
validation: Dataset({
features: ['text', 'labels'],
num_rows: 7948
})
})
```
## Dataset Creation
### Curation Rationale
The dataset was built to train models for the automatic extraction of a knowledge graph based from the scientific literature. The dataset can be used to train character-based models for text segmentation and named entity recognition.
### Source Data
#### Initial Data Collection and Normalization
Figure legends were annotated according to the SourceData framework described in Liechti et al 2017 (Nature Methods, 2017, https://doi.org/10.1038/nmeth.4471). The curation tool at https://curation.sourcedata.io was used to segment figure legends into panel legends, tag enities, assign experiemental roles and normalize with standard identifiers (not available in this dataset). The source data was downloaded from the SourceData API (https://api.sourcedata.io) on 21 Jan 2021.
#### Who are the source language producers?
The examples are extracted from the figure legends from scientific papers in cell and molecular biology.
### Annotations
#### Annotation process
The annotations were produced manually with expert curators from the SourceData project (https://sourcedata.embo.org)
#### Who are the annotators?
Curators of the SourceData project.
### Personal and Sensitive Information
None known.
## Considerations for Using the Data
### Social Impact of Dataset
Not applicable.
### Discussion of Biases
The examples are heavily biased towards cell and molecular biology and are enriched in examples from papers published in EMBO Press journals (https://embopress.org)
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Thomas Lemberger, EMBO.
### Licensing Information
CC BY 4.0
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@tlemberger](https://github.com/tlemberger>) and [@drAbreu](https://github.com/drAbreu>) for adding this dataset. | 8,837 | [
[
-0.035552978515625,
-0.0496826171875,
0.0161285400390625,
0.01561737060546875,
-0.0193634033203125,
0.00949859619140625,
-0.0090179443359375,
-0.015045166015625,
0.053741455078125,
0.032012939453125,
-0.044708251953125,
-0.059051513671875,
-0.037200927734375,
... |
heegyu/kowikitext | 2022-10-02T05:07:59.000Z | [
"license:cc-by-sa-3.0",
"region:us"
] | heegyu | 한국어 위키피디아 article | @InProceedings{huggingface:dataset,
title = {kowikitext},
author={Wikipedia},
year={2022}
} | 1 | 11 | 2022-10-02T02:40:05 | ---
license: cc-by-sa-3.0
---
한국어 위키피디아 article 덤프(20221001)
- 1334694 rows
- download size: 474MB
```python
from datasets import load_dataset
ds = load_dataset("heegyu/kowikitext", "20221001")
ds["train"][0]
```
```
{'id': '5',
'revid': '595831',
'url': 'https://ko.wikipedia.org/wiki?curid=5',
'title': '지미 카터',
'text': '제임스 얼 카터 주니어(, 1924년 10월 1일 ~ )는 민주당 출신 미국 39대 대통령 (1977년 ~ 1981년)이다.\n생애.\n어린 시절.\n지미 카터는 조지아주 섬터 카운티 플레인스 마을에서 태어났다.\n조지아 공과대학교를 졸업하였다. 그 후 해군에 들어가 전함·원자력·잠수함의 승무원으로 일하였다. 1953년 미국 해군 대위로 예편하였고 이후 땅콩·면화 등을 가꿔 많은 돈을 벌었다. 그의 별명이 "땅콩 농부" (Peanut Farmer)로 알려졌다.\n정계 입문.\n1962년 조지아주 상원 의원 선거에서 낙선하나 그 선거가 부정선거 였음을 ... "
}
```
| 654 | [
[
-0.0308837890625,
-0.03851318359375,
0.0119476318359375,
0.04437255859375,
-0.0201263427734375,
-0.0195159912109375,
-0.00390625,
-0.02203369140625,
0.032745361328125,
0.03216552734375,
-0.032623291015625,
-0.03802490234375,
-0.0294952392578125,
0.0354614257... |
arbml/AQAD | 2022-10-14T22:35:38.000Z | [
"region:us"
] | arbml | null | null | 1 | 11 | 2022-10-14T22:35:33 | ---
dataset_info:
features:
- name: id
dtype: string
- name: title
dtype: string
- name: context
dtype: string
- name: question
dtype: string
- name: answers
sequence:
- name: text
dtype: string
- name: answer_start
dtype: int32
splits:
- name: train
num_bytes: 23343014
num_examples: 17911
download_size: 3581662
dataset_size: 23343014
---
# Dataset Card for "AQAD"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 567 | [
[
-0.044769287109375,
-0.019317626953125,
0.00876617431640625,
0.00997161865234375,
-0.00864410400390625,
0.005489349365234375,
0.03387451171875,
-0.004970550537109375,
0.0570068359375,
0.036285400390625,
-0.063720703125,
-0.05755615234375,
-0.0369873046875,
-... |
arbml/SANAD | 2022-10-30T23:09:16.000Z | [
"region:us"
] | arbml | null | null | 0 | 11 | 2022-10-30T23:08:02 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
AlekseyKorshuk/quora-question-pairs | 2022-11-09T13:23:25.000Z | [
"region:us"
] | AlekseyKorshuk | null | null | 0 | 11 | 2022-11-09T13:22:55 | Entry not found | 15 | [
[
-0.021392822265625,
-0.01494598388671875,
0.05718994140625,
0.028839111328125,
-0.0350341796875,
0.046539306640625,
0.052490234375,
0.00507354736328125,
0.051361083984375,
0.01702880859375,
-0.052093505859375,
-0.01494598388671875,
-0.06036376953125,
0.03790... |
PM-AI/germandpr-beir | 2022-11-26T13:04:33.000Z | [
"task_categories:sentence-similarity",
"task_categories:feature-extraction",
"task_categories:text-retrieval",
"task_categories:question-answering",
"task_categories:other",
"task_ids:document-retrieval",
"task_ids:open-domain-qa",
"task_ids:closed-domain-qa",
"multilinguality:monolingual",
"size_... | PM-AI | null | null | 1 | 11 | 2022-11-25T12:28:49 | ---
annotations_creators: []
language:
- de
language_creators: []
license: []
multilinguality:
- monolingual
pretty_name: germandpr-beir
size_categories:
- 10K<n<100K
source_datasets: []
tags:
- information retrieval
- ir
- documents retrieval
- passage retrieval
- beir
- benchmark
- qrel
- sts
- semantic search
task_categories:
- sentence-similarity
- feature-extraction
- text-retrieval
- question-answering
- other
task_ids:
- document-retrieval
- open-domain-qa
- closed-domain-qa
viewer: true
---
# Dataset Card for germanDPR-beir
## Dataset Summary
This dataset can be used for [BEIR](https://arxiv.org/abs/2104.08663) evaluation based on [deepset/germanDPR](https://huggingface.co/datasets/deepset/germandpr).
It already has been used to evaluate a newly trained [bi-encoder model](https://huggingface.co/PM-AI/bi-encoder_msmarco_bert-base_german).
The benchmark framework requires a particular dataset structure by default which has been created locally and uploaded here.
Acknowledgement: The dataset was initially created as "[germanDPR](https://www.deepset.ai/germanquad)" by Timo Möller, Julian Risch, Malte Pietsch, Julian Gutsch, Tom Hersperger, Luise Köhler, Iuliia Mozhina, and Justus Peter, during work done at deepset.ai.
## Dataset Creation
First, the original dataset [deepset/germanDPR](https://huggingface.co/datasets/deepset/germandpr) was converted into three files for BEIR compatibility:
- The first file is `queries.jsonl` and contains an ID and a question in each line.
- The second file, `corpus.jsonl`, contains in each line an ID, a title, a text and some metadata.
- In the `qrel` folder is the third file. It connects every question from `queries.json` (via `q_id`) with a relevant text/answer from `corpus.jsonl` (via `c_id`)
This process has been done for `train` and `test` split separately based on the original germanDPR dataset.
Approaching the dataset creation like that is necessary because queries AND corpus both differ in deepset's germanDPR dataset
and it might be confusion changing this specific split.
In conclusion, queries and corpus differ between train and test split and not only qrels data!
Note: If you want one big corpus use `datasets.concatenate_datasets()`.
In the original dataset, there is one passage containing the answer and three "wrong" passages for each question.
During the creation of this customized dataset, all four passages are added, but only if they are not already present (... meaning they have been deduplicated).
It should be noted, that BEIR is combining `title` + `text` in `corpus.jsonl` to a new string which may produce odd results:
The original germanDPR dataset does not always contain "classical" titles (i.e. short), but sometimes consists of whole sentences, which are also present in the "text" field.
This results in very long passages as well as duplications.
In addition, both title and text contain specially formatted content.
For example, the words used in titles are often connected with underscores:
> `Apple_Magic_Mouse`
And texts begin with special characters to distinguish headings and subheadings:
> `Wirtschaft_der_Vereinigten_Staaten\n\n== Verschuldung ==\nEin durchschnittlicher Haushalt (...)`
Line breaks are also frequently found, as you can see.
Of course, it depends on the application whether these things become a problem or not.
However, it was decided to release two variants of the original dataset:
- The `original` variant leaves the titles and texts as they are. There are no modifications.
- The `processed` variant removes the title completely and simplifies the texts by removing the special formatting.
The creation of both variants can be viewed in [create_dataset.py](https://huggingface.co/datasets/PM-AI/germandpr-beir/resolve/main/create_dataset.py).
In particular, the following parameters were used:
- `original`: `SPLIT=test/train, TEXT_PREPROCESSING=False, KEEP_TITLE=True`
- `processed`: `SPLIT=test/Train, TEXT_PREPROCESSING=True, KEEP_TITLE=False`
One final thing to mention: The IDs for queries and the corpus should not match!!!
During the evaluation using BEIR, it was found that if these IDs match, the result for that entry is completely removed.
This means some of the results are missing.
A correct calculation of the overall result is no longer possible.
Have a look into [BEIR's evaluation.py](https://github.com/beir-cellar/beir/blob/c3334fd5b336dba03c5e3e605a82fcfb1bdf667d/beir/retrieval/evaluation.py#L49) for further understanding.
## Dataset Usage
As earlier mentioned, this dataset is intended to be used with the BEIR benchmark framework.
The file and data structure required for BEIR can only be used to a limited extent with Huggingface Datasets or it is necessary to define multiple dataset repositories at once.
To make it easier, the [dl_dataset.py](https://huggingface.co/datasets/PM-AI/germandpr-beir/tree/main/dl_dataset.py) script is provided to download the dataset and to ensure the correct file and folder structure.
```python
# dl_dataset.py
import json
import os
import datasets
from beir.datasets.data_loader import GenericDataLoader
# ----------------------------------------
# This scripts downloads the BEIR compatible deepsetDPR dataset from "Huggingface Datasets" to your local machine.
# Please see dataset's description/readme to learn more about how the dataset was created.
# If you want to use deepset/germandpr without any changes, use TYPE "original"
# If you want to reproduce PM-AI/bi-encoder_msmarco_bert-base_german, use TYPE "processed"
# ----------------------------------------
TYPE = "processed" # or "original"
SPLIT = "train" # or "train"
DOWNLOAD_DIR = "germandpr-beir-dataset"
DOWNLOAD_DIR = os.path.join(DOWNLOAD_DIR, f'{TYPE}/{SPLIT}')
DOWNLOAD_QREL_DIR = os.path.join(DOWNLOAD_DIR, f'qrels/')
os.makedirs(DOWNLOAD_QREL_DIR, exist_ok=True)
# for BEIR compatibility we need queries, corpus and qrels all together
# ensure to always load these three based on the same type (all "processed" or all "original")
for subset_name in ["queries", "corpus", "qrels"]:
subset = datasets.load_dataset("PM-AI/germandpr-beir", f'{TYPE}-{subset_name}', split=SPLIT)
if subset_name == "qrels":
out_path = os.path.join(DOWNLOAD_QREL_DIR, f'{SPLIT}.tsv')
subset.to_csv(out_path, sep="\t", index=False)
else:
if subset_name == "queries":
_row_to_json = lambda row: json.dumps({"_id": row["_id"], "text": row["text"]}, ensure_ascii=False)
else:
_row_to_json = lambda row: json.dumps({"_id": row["_id"], "title": row["title"], "text": row["text"]}, ensure_ascii=False)
with open(os.path.join(DOWNLOAD_DIR, f'{subset_name}.jsonl'), "w", encoding="utf-8") as out_file:
for row in subset:
out_file.write(_row_to_json(row) + "\n")
# GenericDataLoader is part of BEIR. If everything is working correctly we can now load the dataset
corpus, queries, qrels = GenericDataLoader(data_folder=DOWNLOAD_DIR).load(SPLIT)
print(f'{SPLIT} corpus size: {len(corpus)}\n'
f'{SPLIT} queries size: {len(queries)}\n'
f'{SPLIT} qrels: {len(qrels)}\n')
print("--------------------------------------------------------------------------------------------------------------\n"
"Now you can use the downloaded files in BEIR framework\n"
"Example: https://github.com/beir-cellar/beir/blob/v1.0.1/examples/retrieval/evaluation/dense/evaluate_sbert.py\n"
"--------------------------------------------------------------------------------------------------------------")
```
Alternatively, the data sets can be downloaded directly:
- https://huggingface.co/datasets/PM-AI/germandpr-beir/resolve/main/data/original.tar.gz
- https://huggingface.co/datasets/PM-AI/germandpr-beir/resolve/main/data/processed.tar.gz
Now you can use the downloaded files in BEIR framework:
- For Example: [evaluate_sbert.py](https://github.com/beir-cellar/beir/blob/v1.0.1/examples/retrieval/evaluation/dense/evaluate_sbert.py)
- Just set variable `"dataset"` to `"germandpr-beir-dataset/processed/test"` or `"germandpr-beir-dataset/original/test"`.
- Same goes for `"train"`.
## Dataset Sizes
- Original **train** `corpus` size, `queries` size and `qrels` size: `24009`, `9275` and `9275`
- Original **test** `corpus` size, `queries` size and `qrels` size: `2876`, `1025` and `1025`
- Processed **train** `corpus` size, `queries` size and `qrels` size: `23993`, `9275` and `9275`
- Processed **test** `corpus` size, `queries` size and `qrels` size: `2875` and `1025` and `1025`
## Languages
This dataset only supports german (aka. de, DE).
## Acknowledgment
The dataset was initially created as "[deepset/germanDPR](https://www.deepset.ai/germanquad)" by Timo Möller, Julian Risch, Malte Pietsch, Julian Gutsch, Tom Hersperger, Luise Köhler, Iuliia Mozhina, and Justus Peter, during work done at [deepset.ai](https://www.deepset.ai/).
This work is a collaboration between [Technical University of Applied Sciences Wildau (TH Wildau)](https://en.th-wildau.de/) and [sense.ai.tion GmbH](https://senseaition.com/).
You can contact us via:
* [Philipp Müller (M.Eng.)](https://www.linkedin.com/in/herrphilipps); Author
* [Prof. Dr. Janett Mohnke](mailto:icampus@th-wildau.de); TH Wildau
* [Dr. Matthias Boldt, Jörg Oehmichen](mailto:info@senseaition.com); sense.AI.tion GmbH
This work was funded by the European Regional Development Fund (EFRE) and the State of Brandenburg. Project/Vorhaben: "ProFIT: Natürlichsprachliche Dialogassistenten in der Pflege".
<div style="display:flex">
<div style="padding-left:20px;">
<a href="https://efre.brandenburg.de/efre/de/"><img src="https://huggingface.co/datasets/PM-AI/germandpr-beir/resolve/main/res/EFRE-Logo_rechts_oweb_en_rgb.jpeg" alt="Logo of European Regional Development Fund (EFRE)" width="200"/></a>
</div>
<div style="padding-left:20px;">
<a href="https://www.senseaition.com"><img src="https://senseaition.com/wp-content/uploads/thegem-logos/logo_c847aaa8f42141c4055d4a8665eb208d_3x.png" alt="Logo of senseaition GmbH" width="200"/></a>
</div>
<div style="padding-left:20px;">
<a href="https://www.th-wildau.de"><img src="https://upload.wikimedia.org/wikipedia/commons/thumb/f/f6/TH_Wildau_Logo.png/640px-TH_Wildau_Logo.png" alt="Logo of TH Wildau" width="180"/></a>
</div>
</div> | 10,389 | [
[
-0.042633056640625,
-0.037933349609375,
-0.0020961761474609375,
0.03326416015625,
-0.01251220703125,
-0.0155792236328125,
-0.0216217041015625,
-0.0177001953125,
-0.00461578369140625,
0.0240478515625,
-0.033416748046875,
-0.038116455078125,
-0.025360107421875,
... |
malteos/germeval2017 | 2022-11-30T13:49:08.000Z | [
"language:de",
"region:us"
] | malteos | null | null | 0 | 11 | 2022-11-30T12:53:43 | ---
language:
- de
---
# Germeval Task 2017: Shared Task on Aspect-based Sentiment in Social Media Customer Feedback
In the connected, modern world, customer feedback is a valuable source for insights on the quality of products or services. This feedback allows other customers to benefit from the experiences of others and enables businesses to react on requests, complaints or recommendations. However, the more people use a product or service, the more feedback is generated, which results in the major challenge of analyzing huge amounts of feedback in an efficient, but still meaningful way.
Thus, we propose a shared task on automatically analyzing customer reviews about “Deutsche Bahn” - the german public train operator with about two billion passengers each year.
Example:
> “RT @XXX: Da hört jemand in der Bahn so laut ‘700 Main Street’ durch seine Kopfhörer, dass ich mithören kann. :( :( :(“
As shown in the example, insights from reviews can be derived on different granularities. The review contains a general evaluation of the travel (The customer disliked the travel). Furthermore, the review evaluates a dedicated aspect of the train travel (“laut” → customer did not like the noise level).
Consequently, we frame the task as aspect-based sentiment analysis with four sub tasks:
## Data format
```
ID <tab> Text <tab> Relevance <tab> Sentiment <tab> Aspect:Polarity (whitespace separated)
```
## Links
- http://ltdata1.informatik.uni-hamburg.de/germeval2017/
- https://sites.google.com/view/germeval2017-absa/
## How to cite
```bibtex
@inproceedings{germevaltask2017,
title = {{GermEval 2017: Shared Task on Aspect-based Sentiment in Social Media Customer Feedback}},
author = {Michael Wojatzki and Eugen Ruppert and Sarah Holschneider and Torsten Zesch and Chris Biemann},
year = {2017},
booktitle = {Proceedings of the GermEval 2017 – Shared Task on Aspect-based Sentiment in Social Media Customer Feedback},
address={Berlin, Germany},
pages={1--12}
}
``` | 1,989 | [
[
-0.042938232421875,
-0.0462646484375,
0.0391845703125,
0.0416259765625,
-0.035064697265625,
-0.004558563232421875,
-0.0054473876953125,
-0.052886962890625,
0.048370361328125,
0.02435302734375,
-0.0406494140625,
-0.051422119140625,
-0.037353515625,
-0.0057182... |
egm517/hupd_augmented | 2022-12-10T19:02:49.000Z | [
"task_categories:fill-mask",
"task_categories:summarization",
"task_categories:text-classification",
"task_categories:token-classification",
"task_ids:masked-language-modeling",
"task_ids:multi-class-classification",
"task_ids:topic-classification",
"task_ids:named-entity-recognition",
"language:en"... | egm517 | The Harvard USPTO Patent Dataset (HUPD) is a large-scale, well-structured, and multi-purpose corpus
of English-language patent applications filed to the United States Patent and Trademark Office (USPTO)
between 2004 and 2018. With more than 4.5 million patent documents, HUPD is two to three times larger
than comparable corpora. Unlike other NLP patent datasets, HUPD contains the inventor-submitted versions
of patent applications, not the final versions of granted patents, allowing us to study patentability at
the time of filing using NLP methods for the first time. | @InProceedings{suzgun2021:hupd,
title = {The Harvard USPTO Patent Dataset},
authors={Mirac Suzgun and Suproteem Sarkar and Luke Melas-Kyriazi and Scott Kominers and Stuart Shieber},
year={2021}
} | 0 | 11 | 2022-12-03T02:16:04 | ---
language:
- en
license:
- cc-by-sa-4.0
task_categories:
- fill-mask
- summarization
- text-classification
- token-classification
task_ids:
- masked-language-modeling
- multi-class-classification
- topic-classification
- named-entity-recognition
pretty_name: "HUPD"
tags:
- patents
---
# Dataset Card for The Harvard USPTO Patent Dataset (HUPD)
## Dataset Description
- **Homepage:** [https://patentdataset.org/](https://patentdataset.org/)
- **Repository:** [HUPD GitHub repository](https://github.com/suzgunmirac/hupd)
- **Paper:** [HUPD arXiv Submission](https://arxiv.org/abs/2207.04043)
- **Point of Contact:** Mirac Suzgun
### Dataset Summary
The Harvard USPTO Dataset (HUPD) is a large-scale, well-structured, and multi-purpose corpus of English-language utility patent applications filed to the United States Patent and Trademark Office (USPTO) between January 2004 and December 2018.
### Experiments and Tasks Considered in the Paper
- **Patent Acceptance Prediction**: Given a section of a patent application (in particular, the abstract, claims, or description), predict whether the application will be accepted by the USPTO.
- **Automated Subject (IPC/CPC) Classification**: Predict the primary IPC or CPC code of a patent application given (some subset of) the text of the application.
- **Language Modeling**: Masked/autoregressive language modeling on the claims and description sections of patent applications.
- **Abstractive Summarization**: Given the claims or claims section of a patent application, generate the abstract.
### Languages
The dataset contains English text only.
### Domain
Patents (intellectual property).
### Dataset Curators
The dataset was created by Mirac Suzgun, Luke Melas-Kyriazi, Suproteem K. Sarkar, Scott Duke Kominers, and Stuart M. Shieber.
## Dataset Structure
Each patent application is defined by a distinct JSON file, named after its application number, and includes information about
the application and publication numbers,
title,
decision status,
filing and publication dates,
primary and secondary classification codes,
inventor(s),
examiner,
attorney,
abstract,
claims,
background,
summary, and
full description of the proposed invention, among other fields. There are also supplementary variables, such as the small-entity indicator (which denotes whether the applicant is considered to be a small entity by the USPTO) and the foreign-filing indicator (which denotes whether the application was originally filed in a foreign country).
In total, there are 34 data fields for each application. A full list of data fields used in the dataset is listed in the next section.
### Data Instances
Each patent application in our patent dataset is defined by a distinct JSON file (e.g., ``8914308.json``), named after its unique application number. The format of the JSON files is as follows:
```python
{
"application_number": "...",
"publication_number": "...",
"title": "...",
"decision": "...",
"date_produced": "...",
"date_published": "...",
"main_cpc_label": "...",
"cpc_labels": ["...", "...", "..."],
"main_ipcr_label": "...",
"ipcr_labels": ["...", "...", "..."],
"patent_number": "...",
"filing_date": "...",
"patent_issue_date": "...",
"abandon_date": "...",
"uspc_class": "...",
"uspc_subclass": "...",
"examiner_id": "...",
"examiner_name_last": "...",
"examiner_name_first": "...",
"examiner_name_middle": "...",
"inventor_list": [
{
"inventor_name_last": "...",
"inventor_name_first": "...",
"inventor_city": "...",
"inventor_state": "...",
"inventor_country": "..."
}
],
"abstract": "...",
"claims": "...",
"background": "...",
"summary": "...",
"full_description": "..."
}
```
## Usage
### Loading the Dataset
#### Sample (January 2016 Subset)
The following command can be used to load the `sample` version of the dataset, which contains all the patent applications that were filed to the USPTO during the month of January in 2016. This small subset of the dataset can be used for debugging and exploration purposes.
```python
from datasets import load_dataset
dataset_dict = load_dataset('HUPD/hupd',
name='sample',
data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather",
icpr_label=None,
train_filing_start_date='2016-01-01',
train_filing_end_date='2016-01-21',
val_filing_start_date='2016-01-22',
val_filing_end_date='2016-01-31',
)
```
#### Full Dataset
If you would like to use the **full** version of the dataset, please make sure that change the `name` field from `sample` to `all`, specify the training and validation start and end dates carefully, and set `force_extract` to be `True` (so that you would only untar the files that you are interested in and not squander your disk storage space). In the following example, for instance, we set the training set year range to be [2011, 2016] (inclusive) and the validation set year range to be 2017.
```python
from datasets import load_dataset
dataset_dict = load_dataset('HUPD/hupd',
name='all',
data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather",
icpr_label=None,
force_extract=True,
train_filing_start_date='2011-01-01',
train_filing_end_date='2016-12-31',
val_filing_start_date='2017-01-01',
val_filing_end_date='2017-12-31',
)
```
### Google Colab Notebook
You can also use the following Google Colab notebooks to explore HUPD.
- [](https://colab.research.google.com/drive/1_ZsI7WFTsEO0iu_0g3BLTkIkOUqPzCET?usp=sharing)[ HUPD Examples: Loading the Dataset](https://colab.research.google.com/drive/1_ZsI7WFTsEO0iu_0g3BLTkIkOUqPzCET?usp=sharing)
- [](https://colab.research.google.com/drive/1TzDDCDt368cUErH86Zc_P2aw9bXaaZy1?usp=sharing)[ HUPD Examples: Loading HUPD By Using HuggingFace's Libraries](https://colab.research.google.com/drive/1TzDDCDt368cUErH86Zc_P2aw9bXaaZy1?usp=sharing)
- [](https://colab.research.google.com/drive/1TzDDCDt368cUErH86Zc_P2aw9bXaaZy1?usp=sharing)[ HUPD Examples: Using the HUPD DistilRoBERTa Model](https://colab.research.google.com/drive/11t69BWcAVXndQxAOCpKaGkKkEYJSfydT?usp=sharing)
- [](https://colab.research.google.com/drive/1TzDDCDt368cUErH86Zc_P2aw9bXaaZy1?usp=sharing)[ HUPD Examples: Using the HUPD T5-Small Summarization Model](https://colab.research.google.com/drive/1VkCtrRIryzev_ixDjmJcfJNK-q6Vx24y?usp=sharing)
## Dataset Creation
### Source Data
HUPD synthesizes multiple data sources from the USPTO: While the full patent application texts were obtained from the USPTO Bulk Data Storage System (Patent Application Data/XML Versions 4.0, 4.1, 4.2, 4.3, 4.4 ICE, as well as Version 1.5) as XML files, the bibliographic filing metadata were obtained from the USPTO Patent Examination Research Dataset (in February, 2021).
### Annotations
Beyond our patent decision label, for which construction details are provided in the paper, the dataset does not contain any human-written or computer-generated annotations beyond those produced by patent applicants or the USPTO.
### Data Shift
A major feature of HUPD is its structure, which allows it to demonstrate the evolution of concepts over time. As we illustrate in the paper, the criteria for patent acceptance evolve over time at different rates, depending on category. We believe this is an important feature of the dataset, not only because of the social scientific questions it raises, but also because it facilitates research on models that can accommodate concept shift in a real-world setting.
### Personal and Sensitive Information
The dataset contains information about the inventor(s) and examiner of each patent application. These details are, however, already in the public domain and available on the USPTO's Patent Application Information Retrieval (PAIR) system, as well as on Google Patents and PatentsView.
### Social Impact of the Dataset
The authors of the dataset hope that HUPD will have a positive social impact on the ML/NLP and Econ/IP communities. They discuss these considerations in more detail in [the paper](https://arxiv.org/abs/2207.04043).
### Impact on Underserved Communities and Discussion of Biases
The dataset contains patent applications in English, a language with heavy attention from the NLP community. However, innovation is spread across many languages, cultures, and communities that are not reflected in this dataset. HUPD is thus not representative of all kinds of innovation. Furthermore, patent applications require a fixed cost to draft and file and are not accessible to everyone. One goal of this dataset is to spur research that reduces the cost of drafting applications, potentially allowing for more people to seek intellectual property protection for their innovations.
### Discussion of Biases
Section 4 of [the HUPD paper](https://arxiv.org/abs/2207.04043) provides an examination of the dataset for potential biases. It shows, among other things, that female inventors are notably underrepresented in the U.S. patenting system, that small and micro entities (e.g., independent inventors, small companies, non-profit organizations) are less likely to have positive outcomes in patent obtaining than large entities (e.g., companies with more than 500 employees), and that patent filing and acceptance rates are not uniformly distributed across the US. Our empirical findings suggest that any study focusing on the acceptance prediction task, especially if it is using the inventor information or the small-entity indicator as part of the input, should be aware of the the potential biases present in the dataset and interpret their results carefully in light of those biases.
- Please refer to Section 4 and Section D for an in-depth discussion of potential biases embedded in the dataset.
### Licensing Information
HUPD is released under the CreativeCommons Attribution-NonCommercial-ShareAlike 4.0 International.
### Citation Information
```
@article{suzgun2022hupd,
title={The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications},
author={Suzgun, Mirac and Melas-Kyriazi, Luke and Sarkar, Suproteem K. and Kominers, Scott Duke and Shieber, Stuart M.},
year={2022},
publisher={arXiv preprint arXiv:2207.04043},
url={https://arxiv.org/abs/2207.04043},
``` | 10,874 | [
[
-0.0250244140625,
-0.036865234375,
0.0110931396484375,
0.031646728515625,
-0.01465606689453125,
-0.009063720703125,
0.009857177734375,
-0.0296630859375,
0.0215911865234375,
0.0230255126953125,
-0.007335662841796875,
-0.046051025390625,
-0.0286712646484375,
0... |
nuprl/MultiPL-E-raw-data | 2022-12-20T18:40:05.000Z | [
"license:bsd-3-clause",
"arxiv:2208.08227",
"region:us"
] | nuprl | null | null | 0 | 11 | 2022-12-11T19:07:19 | ---
license: bsd-3-clause
---
# MultiPL-E Evaluation Raw Data
This is the raw data for the MultiPL-E paper: https://arxiv.org/abs/2208.08227 | 142 | [
[
-0.022308349609375,
-0.029937744140625,
0.0169525146484375,
0.02398681640625,
-0.01036834716796875,
0.01132965087890625,
0.0151824951171875,
-0.0038967132568359375,
0.0246124267578125,
0.0294189453125,
-0.052398681640625,
-0.0223388671875,
-0.0251312255859375,
... |
bond005/rulibrispeech | 2023-01-18T19:38:48.000Z | [
"region:us"
] | bond005 | null | null | 0 | 11 | 2022-12-26T10:39:04 | ---
dataset_info:
features:
- name: audio
dtype: audio
- name: transcription
dtype: string
splits:
- name: train
num_bytes: 11165185580.744
num_examples: 54472
- name: test
num_bytes: 306649969.0
num_examples: 1352
- name: validation
num_bytes: 321842480.0
num_examples: 1400
download_size: 10689335725
dataset_size: 11793678029.744
---
# Dataset Card for "rulibrispeech"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 554 | [
[
-0.0341796875,
-0.01422882080078125,
0.00043702125549316406,
0.026397705078125,
-0.01363372802734375,
-0.0045928955078125,
0.023529052734375,
-0.01148223876953125,
0.06280517578125,
0.0306854248046875,
-0.0706787109375,
-0.0450439453125,
-0.03692626953125,
-... |
saibo/bookcorpus_compact_1024 | 2023-01-10T11:48:52.000Z | [
"size_categories:100K<n<1M",
"region:us"
] | saibo | null | null | 0 | 11 | 2022-12-30T01:45:52 | ---
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 2753205189
num_examples: 616051
download_size: 1603181006
dataset_size: 2753205189
size_categories:
- 100K<n<1M
---
# Dataset Card for "bookcorpus_compact_1024"
Num samples: 616,051
The number of tokens for each sequence is not exactly 1024, but all slightly shorter than 1024.
The sequences were built by merging sentences to the maximal length shorter than 1024 tokens.
Therefore, padding is necessary for batch processing.
```python
import time
from typing import List
from datasets import load_dataset, Dataset
from tqdm import tqdm
from transformers import AutoTokenizer
def batch_tokenize(texts: List[str], tokenizer, batch_size=1000):
start = time.time()
"""Tokenize the texts in batch"""
assert tokenizer.is_fast, "tokenizer must be fast tokenizer"
tokenized_texts = []
for i in tqdm(range(0, len(texts), batch_size)):
batch = texts[i:i + batch_size]
batch_encoding = tokenizer(batch)
tokenized_texts.extend(batch_encoding["input_ids"])
print(f"batch_tokenize time with bs={batch_size}: {time.time() - start}")
return tokenized_texts
class CompactText:
def __init__(self, tokenizer="gpt2", split="test", block_size=512):
self.block_size = block_size
self.tokenizer = AutoTokenizer.from_pretrained(tokenizer)
def compact_load(self, dataset_name: str, split: str):
dataset = load_dataset(dataset_name)[split]
batch_encoding = batch_tokenize(dataset["text"], self.tokenizer, batch_size=10000)
compact_texts = []
texts = dataset["text"]
total_num_tok = 0
tracker = []
i = 0
for j in tqdm(range(len(batch_encoding))):
total_num_tok += len(batch_encoding[j])
if total_num_tok >= self.block_size:
batch_sents = texts[i:j]
big_sent = " ".join(batch_sents)
compact_texts.append(big_sent)
tracker.append((i, j))
i = j
total_num_tok = 0
print(tracker)
# self.examples = compact_texts
compact_ds = Dataset.from_dict({"text": compact_texts})
return compact_ds
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("-b", "--block-size", type=int, default=512)
args = parser.parse_args()
compactifier = CompactText(block_size=args.block_size)
dataset = compactifier.compact_load(dataset_name="saibo/bookcorpus_deduplicated", split="train")
dataset.push_to_hub(f"saibo/bookcorpus_compact_{args.block_size}")
```
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 2,837 | [
[
-0.023712158203125,
-0.03594970703125,
0.0239715576171875,
0.0104217529296875,
-0.036773681640625,
-0.00099945068359375,
-0.0260162353515625,
-0.0029125213623046875,
-0.00506591796875,
0.014495849609375,
-0.039764404296875,
-0.037017822265625,
-0.052947998046875... |
irds/wikiclir_vi | 2023-01-05T04:01:17.000Z | [
"task_categories:text-retrieval",
"region:us"
] | irds | null | null | 0 | 11 | 2023-01-05T04:01:11 | ---
pretty_name: '`wikiclir/vi`'
viewer: false
source_datasets: []
task_categories:
- text-retrieval
---
# Dataset Card for `wikiclir/vi`
The `wikiclir/vi` dataset, provided by the [ir-datasets](https://ir-datasets.com/) package.
For more information about the dataset, see the [documentation](https://ir-datasets.com/wikiclir#wikiclir/vi).
# Data
This dataset provides:
- `docs` (documents, i.e., the corpus); count=1,392,152
- `queries` (i.e., topics); count=354,312
- `qrels`: (relevance assessments); count=611,355
## Usage
```python
from datasets import load_dataset
docs = load_dataset('irds/wikiclir_vi', 'docs')
for record in docs:
record # {'doc_id': ..., 'title': ..., 'text': ...}
queries = load_dataset('irds/wikiclir_vi', 'queries')
for record in queries:
record # {'query_id': ..., 'text': ...}
qrels = load_dataset('irds/wikiclir_vi', 'qrels')
for record in qrels:
record # {'query_id': ..., 'doc_id': ..., 'relevance': ..., 'iteration': ...}
```
Note that calling `load_dataset` will download the dataset (or provide access instructions when it's not public) and make a copy of the
data in 🤗 Dataset format.
## Citation Information
```
@inproceedings{sasaki-etal-2018-cross,
title = "Cross-Lingual Learning-to-Rank with Shared Representations",
author = "Sasaki, Shota and
Sun, Shuo and
Schamoni, Shigehiko and
Duh, Kevin and
Inui, Kentaro",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-2073",
doi = "10.18653/v1/N18-2073",
pages = "458--463"
}
```
| 1,859 | [
[
-0.01922607421875,
-0.0243072509765625,
0.005096435546875,
0.00026297569274902344,
-0.007396697998046875,
-0.0037746429443359375,
-0.029296875,
-0.01215362548828125,
0.03460693359375,
0.01629638671875,
-0.0287017822265625,
-0.05731201171875,
-0.035858154296875,
... |
Norod78/hearthstone-cards-512 | 2023-01-05T18:48:19.000Z | [
"task_categories:text-to-image",
"size_categories:n<10K",
"blizzard",
"hearthstone",
"game cards",
"region:us"
] | Norod78 | null | null | 1 | 11 | 2023-01-05T18:41:08 | ---
dataset_info:
features:
- name: text
dtype: string
- name: image
dtype: image
splits:
- name: train
num_bytes: 230518521.36
num_examples: 2952
download_size: 230628184
dataset_size: 230518521.36
pretty_name: 'Blizzard Hearthstone cards, resized to 512x512 with OCR text field'
size_categories:
- n<10K
tags: ["blizzard", "hearthstone", "game cards"]
task_categories:
- text-to-image
---
# Dataset Card for "hearthstone-cards-512"
# Not affiliated in anyway with Blizzard nor Hearthstone
# Please note that this entrie dataset contains copyrighted matirial | 594 | [
[
-0.003971099853515625,
-0.015228271484375,
-0.0159912109375,
0.0496826171875,
-0.034515380859375,
-0.005237579345703125,
0.0214080810546875,
-0.0130767822265625,
0.04058837890625,
0.07708740234375,
-0.06182861328125,
-0.041046142578125,
-0.0236053466796875,
... |
Cohere/wikipedia-22-12-hi-embeddings | 2023-03-22T16:53:57.000Z | [
"task_categories:text-retrieval",
"task_ids:document-retrieval",
"annotations_creators:expert-generated",
"multilinguality:multilingual",
"language:hi",
"license:apache-2.0",
"region:us"
] | Cohere | null | null | 0 | 11 | 2023-01-13T23:14:15 | ---
annotations_creators:
- expert-generated
language:
- hi
multilinguality:
- multilingual
size_categories: []
source_datasets: []
tags: []
task_categories:
- text-retrieval
license:
- apache-2.0
task_ids:
- document-retrieval
---
# Wikipedia (hi) embedded with cohere.ai `multilingual-22-12` encoder
We encoded [Wikipedia (hi)](https://hi.wikipedia.org) using the [cohere.ai](https://txt.cohere.ai/multilingual/) `multilingual-22-12` embedding model.
To get an overview how this dataset was created and pre-processed, have a look at [Cohere/wikipedia-22-12](https://huggingface.co/datasets/Cohere/wikipedia-22-12).
## Embeddings
We compute for `title+" "+text` the embeddings using our `multilingual-22-12` embedding model, a state-of-the-art model that works for semantic search in 100 languages. If you want to learn more about this model, have a look at [cohere.ai multilingual embedding model](https://txt.cohere.ai/multilingual/).
## Further languages
We provide embeddings of Wikipedia in many different languages:
[ar](https://huggingface.co/datasets/Cohere/wikipedia-22-12-ar-embeddings), [de](https://huggingface.co/datasets/Cohere/wikipedia-22-12-de-embeddings), [en](https://huggingface.co/datasets/Cohere/wikipedia-22-12-en-embeddings), [es](https://huggingface.co/datasets/Cohere/wikipedia-22-12-es-embeddings), [fr](https://huggingface.co/datasets/Cohere/wikipedia-22-12-fr-embeddings), [hi](https://huggingface.co/datasets/Cohere/wikipedia-22-12-hi-embeddings), [it](https://huggingface.co/datasets/Cohere/wikipedia-22-12-it-embeddings), [ja](https://huggingface.co/datasets/Cohere/wikipedia-22-12-ja-embeddings), [ko](https://huggingface.co/datasets/Cohere/wikipedia-22-12-ko-embeddings), [simple english](https://huggingface.co/datasets/Cohere/wikipedia-22-12-simple-embeddings), [zh](https://huggingface.co/datasets/Cohere/wikipedia-22-12-zh-embeddings),
You can find the Wikipedia datasets without embeddings at [Cohere/wikipedia-22-12](https://huggingface.co/datasets/Cohere/wikipedia-22-12).
## Loading the dataset
You can either load the dataset like this:
```python
from datasets import load_dataset
docs = load_dataset(f"Cohere/wikipedia-22-12-hi-embeddings", split="train")
```
Or you can also stream it without downloading it before:
```python
from datasets import load_dataset
docs = load_dataset(f"Cohere/wikipedia-22-12-hi-embeddings", split="train", streaming=True)
for doc in docs:
docid = doc['id']
title = doc['title']
text = doc['text']
emb = doc['emb']
```
## Search
A full search example:
```python
#Run: pip install cohere datasets
from datasets import load_dataset
import torch
import cohere
co = cohere.Client(f"<<COHERE_API_KEY>>") # Add your cohere API key from www.cohere.com
#Load at max 1000 documents + embeddings
max_docs = 1000
docs_stream = load_dataset(f"Cohere/wikipedia-22-12-hi-embeddings", split="train", streaming=True)
docs = []
doc_embeddings = []
for doc in docs_stream:
docs.append(doc)
doc_embeddings.append(doc['emb'])
if len(docs) >= max_docs:
break
doc_embeddings = torch.tensor(doc_embeddings)
query = 'Who founded Youtube'
response = co.embed(texts=[query], model='multilingual-22-12')
query_embedding = response.embeddings
query_embedding = torch.tensor(query_embedding)
# Compute dot score between query embedding and document embeddings
dot_scores = torch.mm(query_embedding, doc_embeddings.transpose(0, 1))
top_k = torch.topk(dot_scores, k=3)
# Print results
print("Query:", query)
for doc_id in top_k.indices[0].tolist():
print(docs[doc_id]['title'])
print(docs[doc_id]['text'], "\n")
```
## Performance
You can find performance on the MIRACL dataset (a semantic search evaluation dataset) here: [miracl-en-queries-22-12#performance](https://huggingface.co/datasets/Cohere/miracl-en-queries-22-12#performance) | 3,845 | [
[
-0.05108642578125,
-0.05084228515625,
0.011138916015625,
0.0006804466247558594,
-0.01117706298828125,
-0.007602691650390625,
-0.023284912109375,
-0.019073486328125,
0.043731689453125,
-0.0000896453857421875,
-0.037353515625,
-0.06292724609375,
-0.045654296875,
... |
matchbench/openea-d-w-15k-v1 | 2023-01-18T11:30:17.000Z | [
"region:us"
] | matchbench | null | null | 0 | 11 | 2023-01-18T11:17:24 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
relbert/semeval2012_relational_similarity | 2023-02-02T15:38:26.000Z | [
"multilinguality:monolingual",
"size_categories:n<1K",
"language:en",
"license:other",
"region:us"
] | relbert | [SemEVAL 2012 task 2: Relational Similarity](https://aclanthology.org/S12-1047/) | @inproceedings{jurgens-etal-2012-semeval,
title = "{S}em{E}val-2012 Task 2: Measuring Degrees of Relational Similarity",
author = "Jurgens, David and
Mohammad, Saif and
Turney, Peter and
Holyoak, Keith",
booktitle = "*{SEM} 2012: The First Joint Conference on Lexical and Computational Semantics {--} Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation ({S}em{E}val 2012)",
month = "7-8 " # jun,
year = "2012",
address = "Montr{\'e}al, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S12-1047",
pages = "356--364",
} | 1 | 11 | 2023-01-19T14:19:11 | ---
language:
- en
license:
- other
multilinguality:
- monolingual
size_categories:
- n<1K
pretty_name: SemEval2012 relational similarity dataset
---
# Dataset Card for "relbert/semeval2012_relational_similarity"
## Dataset Description
- **Repository:** [RelBERT](https://github.com/asahi417/relbert)
- **Paper:** [https://aclanthology.org/S12-1047/](https://aclanthology.org/S12-1047/)
- **Dataset:** SemEval2012 relational similarity dataset
### Dataset Summary
Relational similarity dataset from [SemEval2012 task 2](https://aclanthology.org/S12-1047/), compiled to fine-tune [RelBERT](https://github.com/asahi417/relbert) model.
The dataset contains a list of positive and negative word pair from 89 pre-defined relations.
The relation types are constructed on top of following 10 parent relation types.
```shell
{
1: "Class Inclusion", # Hypernym
2: "Part-Whole", # Meronym, Substance Meronym
3: "Similar", # Synonym, Co-hypornym
4: "Contrast", # Antonym
5: "Attribute", # Attribute, Event
6: "Non Attribute",
7: "Case Relation",
8: "Cause-Purpose",
9: "Space-Time",
10: "Representation"
}
```
Each of the parent relation is further grouped into child relation types where the definition can be found [here](https://drive.google.com/file/d/0BzcZKTSeYL8VenY0QkVpZVpxYnc/view?resourcekey=0-ZP-UARfJj39PcLroibHPHw).
## Dataset Structure
### Data Instances
An example of `train` looks as follows.
```shell
{
'relation_type': '8d',
'positives': [ [ "breathe", "live" ], [ "study", "learn" ], [ "speak", "communicate" ], ... ]
'negatives': [ [ "starving", "hungry" ], [ "clean", "bathe" ], [ "hungry", "starving" ], ... ]
}
```
### Data Splits
|train|validation|
|----:|---------:|
| 79 | 79 |
## Citation Information
```
@inproceedings{jurgens-etal-2012-semeval,
title = "{S}em{E}val-2012 Task 2: Measuring Degrees of Relational Similarity",
author = "Jurgens, David and
Mohammad, Saif and
Turney, Peter and
Holyoak, Keith",
booktitle = "*{SEM} 2012: The First Joint Conference on Lexical and Computational Semantics {--} Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation ({S}em{E}val 2012)",
month = "7-8 " # jun,
year = "2012",
address = "Montr{\'e}al, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S12-1047",
pages = "356--364",
}
``` | 2,516 | [
[
-0.029388427734375,
-0.041534423828125,
0.0194549560546875,
0.0151824951171875,
-0.022430419921875,
-0.0208587646484375,
-0.00644683837890625,
-0.013397216796875,
0.0308380126953125,
0.019439697265625,
-0.0672607421875,
-0.06329345703125,
-0.041015625,
0.021... |
jonathan-roberts1/SIRI-WHU | 2023-03-31T17:18:08.000Z | [
"task_categories:image-classification",
"task_categories:zero-shot-image-classification",
"license:other",
"region:us"
] | jonathan-roberts1 | null | null | 1 | 11 | 2023-01-20T15:46:58 | ---
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': agriculture
'1': commercial
'2': harbor
'3': idle_land
'4': industrial
'5': meadow
'6': overpass
'7': park
'8': pond
'9': residential
'10': river
'11': water
splits:
- name: train
num_bytes: 158215614.4
num_examples: 2400
download_size: 147702566
dataset_size: 158215614.4
license: other
task_categories:
- image-classification
- zero-shot-image-classification
---
# Dataset Card for "SIRI-WHU"
## Dataset Description
- **Paper** [Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery](https://ieeexplore.ieee.org/iel7/36/4358825/07329997.pdf)
- **Paper** [The Fisher kernel coding framework for high spatial resolution scene classification](https://www.mdpi.com/2072-4292/8/2/157/pdf)
- **Paper** [Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery](https://ieeexplore.ieee.org/iel7/8859/7473942/07466064.pdf)
### Licensing Information
CC BY-NC-ND
## Citation Information
[Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery](https://ieeexplore.ieee.org/iel7/36/4358825/07329997.pdf)
[The Fisher kernel coding framework for high spatial resolution scene classification](https://www.mdpi.com/2072-4292/8/2/157/pdf)
[Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery](https://ieeexplore.ieee.org/iel7/8859/7473942/07466064.pdf)
```
@article{zhao2015dirichlet,
title={Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery},
author={Zhao, Bei and Zhong, Yanfei and Xia, Gui-Song and Zhang, Liangpei},
journal={IEEE Transactions on Geoscience and Remote Sensing},
volume={54},
number={4},
pages={2108--2123},
year={2015},
publisher={IEEE}
}
@article{zhao2016fisher,
title={The Fisher kernel coding framework for high spatial resolution scene classification},
author={Zhao, Bei and Zhong, Yanfei and Zhang, Liangpei and Huang, Bo},
journal={Remote Sensing},
volume={8},
number={2},
pages={157},
year={2016},
publisher={MDPI}
}
@article{zhu2016bag,
title={Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery},
author={Zhu, Qiqi and Zhong, Yanfei and Zhao, Bei and Xia, Gui-Song and Zhang, Liangpei},
journal={IEEE Geoscience and Remote Sensing Letters},
volume={13},
number={6},
pages={747--751},
year={2016},
publisher={IEEE}
}
``` | 2,825 | [
[
-0.047760009765625,
-0.032470703125,
0.017608642578125,
0.004291534423828125,
-0.006412506103515625,
-0.0129241943359375,
-0.002994537353515625,
-0.033477783203125,
-0.006946563720703125,
0.020294189453125,
-0.022674560546875,
-0.0499267578125,
-0.04092407226562... |
tj-solergibert/Europarl-ST | 2023-02-09T10:22:06.000Z | [
"task_categories:translation",
"task_categories:text-to-speech",
"size_categories:100K<n<1M",
"language:es",
"language:de",
"language:en",
"language:fr",
"language:nl",
"language:pl",
"language:pt",
"language:ro",
"language:it",
"license:cc-by-nc-4.0",
"region:us"
] | tj-solergibert | null | null | 0 | 11 | 2023-02-08T22:47:18 | ---
dataset_info:
features:
- name: original_speech
dtype: string
- name: original_language
dtype: string
- name: audio_path
dtype: string
- name: segment_start
dtype: float32
- name: segment_end
dtype: float32
- name: transcriptions
struct:
- name: de
dtype: string
- name: en
dtype: string
- name: es
dtype: string
- name: fr
dtype: string
- name: it
dtype: string
- name: nl
dtype: string
- name: pl
dtype: string
- name: pt
dtype: string
- name: ro
dtype: string
splits:
- name: train
num_bytes: 147857910
num_examples: 116138
- name: valid
num_bytes: 21318985
num_examples: 17538
- name: test
num_bytes: 22580968
num_examples: 18901
download_size: 109205144
dataset_size: 191757863
task_categories:
- translation
- text-to-speech
language:
- es
- de
- en
- fr
- nl
- pl
- pt
- ro
- it
size_categories:
- 100K<n<1M
license: cc-by-nc-4.0
---
# Dataset Card for "Europarl-ST"
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://www.mllp.upv.es/europarl-st/
- **Paper:** https://ieeexplore.ieee.org/document/9054626
- **Point of Contact:** https://www.mllp.upv.es/
### Dataset Summary
Europarl-ST is a Multilingual Speech Translation Corpus, that contains paired audio-text samples for Speech Translation, constructed using the debates carried out in the European Parliament in the period between 2008 and 2012.
### Languages
Spanish, German, English, French, Dutch, Polish, Portuguese, Romanian, Italian
## Dataset Structure
### Data Fields
- **original_audio:** The original speech that is heard on the recording.
- **original_language:** The language of the audio
- **audio_path:** Path to the audio file
- **segment_start:** Second in which the speech begins
- **segment_end:** Second in which the speech ends
- **transcriptions:** Dictionary containing transcriptions into different languages
### Data Splits
- **train split:** 116138 samples
- **valid split:** 17538 samples
- **test split:** 18901 samples
Train set (hours):
| src/tgt | en | fr | de | it | es | pt | pl | ro | nl |
|---------|----|----|----|----|----|----|----|----|----|
| en | - | 81 | 83 | 80 | 81 | 81 | 79 | 72 | 80 |
| fr | 32 | - | 21 | 20 | 21 | 22 | 20 | 18 | 22 |
| de | 30 | 18 | - | 17 | 18 | 18 | 17 | 17 | 18 |
| it | 37 | 21 | 21 | - | 21 | 21 | 21 | 19 | 20 |
| es | 22 | 14 | 14 | 14 | - | 14 | 13 | 12 | 13 |
| pt | 15 | 10 | 10 | 10 | 10 | - | 9 | 9 | 9 |
| pl | 28 | 18 | 18 | 17 | 18 | 18 | - | 16 | 18 |
| ro | 24 | 12 | 12 | 12 | 12 | 12 | 12 | - | 12 |
| nl | 7 | 5 | 5 | 4 | 5 | 4 | 4 | 4 | - |
Valid/Test sets are all between 3 and 6 hours.
## Additional Information
### Licensing Information
* The work carried out for constructing the Europarl-ST corpus is released under a Creative Commons Attribution-NonCommercial 4.0 International license (CC BY-NC 4.0)
* All rights of the data belong to the European Union and respective copyright holders.
### Citation Information
If you use the corpus in your research please cite the following reference:
@INPROCEEDINGS{jairsan2020a,
author={J. {Iranzo-Sánchez} and J. A. {Silvestre-Cerdà} and J. {Jorge} and N. {Roselló} and A. {Giménez} and A. {Sanchis} and J. {Civera} and A. {Juan}},
booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates},
year={2020},
pages={8229-8233},} | 4,076 | [
[
-0.048736572265625,
-0.03509521484375,
0.019561767578125,
0.01654052734375,
-0.03424072265625,
-0.004146575927734375,
-0.0271148681640625,
-0.03668212890625,
0.034576416015625,
0.015472412109375,
-0.0411376953125,
-0.0560302734375,
-0.04534912109375,
0.01730... |
Multimodal-Fatima/Imagenet1k_sample_validation | 2023-02-10T18:05:59.000Z | [
"region:us"
] | Multimodal-Fatima | null | null | 0 | 11 | 2023-02-10T18:05:33 | ---
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': tench, Tinca tinca
'1': goldfish, Carassius auratus
'2': great white shark, white shark, man-eater, man-eating shark, Carcharodon
carcharias
'3': tiger shark, Galeocerdo cuvieri
'4': hammerhead, hammerhead shark
'5': electric ray, crampfish, numbfish, torpedo
'6': stingray
'7': cock
'8': hen
'9': ostrich, Struthio camelus
'10': brambling, Fringilla montifringilla
'11': goldfinch, Carduelis carduelis
'12': house finch, linnet, Carpodacus mexicanus
'13': junco, snowbird
'14': indigo bunting, indigo finch, indigo bird, Passerina cyanea
'15': robin, American robin, Turdus migratorius
'16': bulbul
'17': jay
'18': magpie
'19': chickadee
'20': water ouzel, dipper
'21': kite
'22': bald eagle, American eagle, Haliaeetus leucocephalus
'23': vulture
'24': great grey owl, great gray owl, Strix nebulosa
'25': European fire salamander, Salamandra salamandra
'26': common newt, Triturus vulgaris
'27': eft
'28': spotted salamander, Ambystoma maculatum
'29': axolotl, mud puppy, Ambystoma mexicanum
'30': bullfrog, Rana catesbeiana
'31': tree frog, tree-frog
'32': tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui
'33': loggerhead, loggerhead turtle, Caretta caretta
'34': leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea
'35': mud turtle
'36': terrapin
'37': box turtle, box tortoise
'38': banded gecko
'39': common iguana, iguana, Iguana iguana
'40': American chameleon, anole, Anolis carolinensis
'41': whiptail, whiptail lizard
'42': agama
'43': frilled lizard, Chlamydosaurus kingi
'44': alligator lizard
'45': Gila monster, Heloderma suspectum
'46': green lizard, Lacerta viridis
'47': African chameleon, Chamaeleo chamaeleon
'48': Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus
komodoensis
'49': African crocodile, Nile crocodile, Crocodylus niloticus
'50': American alligator, Alligator mississipiensis
'51': triceratops
'52': thunder snake, worm snake, Carphophis amoenus
'53': ringneck snake, ring-necked snake, ring snake
'54': hognose snake, puff adder, sand viper
'55': green snake, grass snake
'56': king snake, kingsnake
'57': garter snake, grass snake
'58': water snake
'59': vine snake
'60': night snake, Hypsiglena torquata
'61': boa constrictor, Constrictor constrictor
'62': rock python, rock snake, Python sebae
'63': Indian cobra, Naja naja
'64': green mamba
'65': sea snake
'66': horned viper, cerastes, sand viper, horned asp, Cerastes cornutus
'67': diamondback, diamondback rattlesnake, Crotalus adamanteus
'68': sidewinder, horned rattlesnake, Crotalus cerastes
'69': trilobite
'70': harvestman, daddy longlegs, Phalangium opilio
'71': scorpion
'72': black and gold garden spider, Argiope aurantia
'73': barn spider, Araneus cavaticus
'74': garden spider, Aranea diademata
'75': black widow, Latrodectus mactans
'76': tarantula
'77': wolf spider, hunting spider
'78': tick
'79': centipede
'80': black grouse
'81': ptarmigan
'82': ruffed grouse, partridge, Bonasa umbellus
'83': prairie chicken, prairie grouse, prairie fowl
'84': peacock
'85': quail
'86': partridge
'87': African grey, African gray, Psittacus erithacus
'88': macaw
'89': sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita
'90': lorikeet
'91': coucal
'92': bee eater
'93': hornbill
'94': hummingbird
'95': jacamar
'96': toucan
'97': drake
'98': red-breasted merganser, Mergus serrator
'99': goose
'100': black swan, Cygnus atratus
'101': tusker
'102': echidna, spiny anteater, anteater
'103': platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus
anatinus
'104': wallaby, brush kangaroo
'105': koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus
'106': wombat
'107': jellyfish
'108': sea anemone, anemone
'109': brain coral
'110': flatworm, platyhelminth
'111': nematode, nematode worm, roundworm
'112': conch
'113': snail
'114': slug
'115': sea slug, nudibranch
'116': chiton, coat-of-mail shell, sea cradle, polyplacophore
'117': chambered nautilus, pearly nautilus, nautilus
'118': Dungeness crab, Cancer magister
'119': rock crab, Cancer irroratus
'120': fiddler crab
'121': king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes
camtschatica
'122': American lobster, Northern lobster, Maine lobster, Homarus americanus
'123': spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish
'124': crayfish, crawfish, crawdad, crawdaddy
'125': hermit crab
'126': isopod
'127': white stork, Ciconia ciconia
'128': black stork, Ciconia nigra
'129': spoonbill
'130': flamingo
'131': little blue heron, Egretta caerulea
'132': American egret, great white heron, Egretta albus
'133': bittern
'134': crane
'135': limpkin, Aramus pictus
'136': European gallinule, Porphyrio porphyrio
'137': American coot, marsh hen, mud hen, water hen, Fulica americana
'138': bustard
'139': ruddy turnstone, Arenaria interpres
'140': red-backed sandpiper, dunlin, Erolia alpina
'141': redshank, Tringa totanus
'142': dowitcher
'143': oystercatcher, oyster catcher
'144': pelican
'145': king penguin, Aptenodytes patagonica
'146': albatross, mollymawk
'147': grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius
robustus
'148': killer whale, killer, orca, grampus, sea wolf, Orcinus orca
'149': dugong, Dugong dugon
'150': sea lion
'151': Chihuahua
'152': Japanese spaniel
'153': Maltese dog, Maltese terrier, Maltese
'154': Pekinese, Pekingese, Peke
'155': Shih-Tzu
'156': Blenheim spaniel
'157': papillon
'158': toy terrier
'159': Rhodesian ridgeback
'160': Afghan hound, Afghan
'161': basset, basset hound
'162': beagle
'163': bloodhound, sleuthhound
'164': bluetick
'165': black-and-tan coonhound
'166': Walker hound, Walker foxhound
'167': English foxhound
'168': redbone
'169': borzoi, Russian wolfhound
'170': Irish wolfhound
'171': Italian greyhound
'172': whippet
'173': Ibizan hound, Ibizan Podenco
'174': Norwegian elkhound, elkhound
'175': otterhound, otter hound
'176': Saluki, gazelle hound
'177': Scottish deerhound, deerhound
'178': Weimaraner
'179': Staffordshire bullterrier, Staffordshire bull terrier
'180': American Staffordshire terrier, Staffordshire terrier, American pit
bull terrier, pit bull terrier
'181': Bedlington terrier
'182': Border terrier
'183': Kerry blue terrier
'184': Irish terrier
'185': Norfolk terrier
'186': Norwich terrier
'187': Yorkshire terrier
'188': wire-haired fox terrier
'189': Lakeland terrier
'190': Sealyham terrier, Sealyham
'191': Airedale, Airedale terrier
'192': cairn, cairn terrier
'193': Australian terrier
'194': Dandie Dinmont, Dandie Dinmont terrier
'195': Boston bull, Boston terrier
'196': miniature schnauzer
'197': giant schnauzer
'198': standard schnauzer
'199': Scotch terrier, Scottish terrier, Scottie
'200': Tibetan terrier, chrysanthemum dog
'201': silky terrier, Sydney silky
'202': soft-coated wheaten terrier
'203': West Highland white terrier
'204': Lhasa, Lhasa apso
'205': flat-coated retriever
'206': curly-coated retriever
'207': golden retriever
'208': Labrador retriever
'209': Chesapeake Bay retriever
'210': German short-haired pointer
'211': vizsla, Hungarian pointer
'212': English setter
'213': Irish setter, red setter
'214': Gordon setter
'215': Brittany spaniel
'216': clumber, clumber spaniel
'217': English springer, English springer spaniel
'218': Welsh springer spaniel
'219': cocker spaniel, English cocker spaniel, cocker
'220': Sussex spaniel
'221': Irish water spaniel
'222': kuvasz
'223': schipperke
'224': groenendael
'225': malinois
'226': briard
'227': kelpie
'228': komondor
'229': Old English sheepdog, bobtail
'230': Shetland sheepdog, Shetland sheep dog, Shetland
'231': collie
'232': Border collie
'233': Bouvier des Flandres, Bouviers des Flandres
'234': Rottweiler
'235': German shepherd, German shepherd dog, German police dog, alsatian
'236': Doberman, Doberman pinscher
'237': miniature pinscher
'238': Greater Swiss Mountain dog
'239': Bernese mountain dog
'240': Appenzeller
'241': EntleBucher
'242': boxer
'243': bull mastiff
'244': Tibetan mastiff
'245': French bulldog
'246': Great Dane
'247': Saint Bernard, St Bernard
'248': Eskimo dog, husky
'249': malamute, malemute, Alaskan malamute
'250': Siberian husky
'251': dalmatian, coach dog, carriage dog
'252': affenpinscher, monkey pinscher, monkey dog
'253': basenji
'254': pug, pug-dog
'255': Leonberg
'256': Newfoundland, Newfoundland dog
'257': Great Pyrenees
'258': Samoyed, Samoyede
'259': Pomeranian
'260': chow, chow chow
'261': keeshond
'262': Brabancon griffon
'263': Pembroke, Pembroke Welsh corgi
'264': Cardigan, Cardigan Welsh corgi
'265': toy poodle
'266': miniature poodle
'267': standard poodle
'268': Mexican hairless
'269': timber wolf, grey wolf, gray wolf, Canis lupus
'270': white wolf, Arctic wolf, Canis lupus tundrarum
'271': red wolf, maned wolf, Canis rufus, Canis niger
'272': coyote, prairie wolf, brush wolf, Canis latrans
'273': dingo, warrigal, warragal, Canis dingo
'274': dhole, Cuon alpinus
'275': African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus
'276': hyena, hyaena
'277': red fox, Vulpes vulpes
'278': kit fox, Vulpes macrotis
'279': Arctic fox, white fox, Alopex lagopus
'280': grey fox, gray fox, Urocyon cinereoargenteus
'281': tabby, tabby cat
'282': tiger cat
'283': Persian cat
'284': Siamese cat, Siamese
'285': Egyptian cat
'286': cougar, puma, catamount, mountain lion, painter, panther, Felis concolor
'287': lynx, catamount
'288': leopard, Panthera pardus
'289': snow leopard, ounce, Panthera uncia
'290': jaguar, panther, Panthera onca, Felis onca
'291': lion, king of beasts, Panthera leo
'292': tiger, Panthera tigris
'293': cheetah, chetah, Acinonyx jubatus
'294': brown bear, bruin, Ursus arctos
'295': American black bear, black bear, Ursus americanus, Euarctos americanus
'296': ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus
'297': sloth bear, Melursus ursinus, Ursus ursinus
'298': mongoose
'299': meerkat, mierkat
'300': tiger beetle
'301': ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle
'302': ground beetle, carabid beetle
'303': long-horned beetle, longicorn, longicorn beetle
'304': leaf beetle, chrysomelid
'305': dung beetle
'306': rhinoceros beetle
'307': weevil
'308': fly
'309': bee
'310': ant, emmet, pismire
'311': grasshopper, hopper
'312': cricket
'313': walking stick, walkingstick, stick insect
'314': cockroach, roach
'315': mantis, mantid
'316': cicada, cicala
'317': leafhopper
'318': lacewing, lacewing fly
'319': dragonfly, darning needle, devil's darning needle, sewing needle,
snake feeder, snake doctor, mosquito hawk, skeeter hawk
'320': damselfly
'321': admiral
'322': ringlet, ringlet butterfly
'323': monarch, monarch butterfly, milkweed butterfly, Danaus plexippus
'324': cabbage butterfly
'325': sulphur butterfly, sulfur butterfly
'326': lycaenid, lycaenid butterfly
'327': starfish, sea star
'328': sea urchin
'329': sea cucumber, holothurian
'330': wood rabbit, cottontail, cottontail rabbit
'331': hare
'332': Angora, Angora rabbit
'333': hamster
'334': porcupine, hedgehog
'335': fox squirrel, eastern fox squirrel, Sciurus niger
'336': marmot
'337': beaver
'338': guinea pig, Cavia cobaya
'339': sorrel
'340': zebra
'341': hog, pig, grunter, squealer, Sus scrofa
'342': wild boar, boar, Sus scrofa
'343': warthog
'344': hippopotamus, hippo, river horse, Hippopotamus amphibius
'345': ox
'346': water buffalo, water ox, Asiatic buffalo, Bubalus bubalis
'347': bison
'348': ram, tup
'349': bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain
sheep, Ovis canadensis
'350': ibex, Capra ibex
'351': hartebeest
'352': impala, Aepyceros melampus
'353': gazelle
'354': Arabian camel, dromedary, Camelus dromedarius
'355': llama
'356': weasel
'357': mink
'358': polecat, fitch, foulmart, foumart, Mustela putorius
'359': black-footed ferret, ferret, Mustela nigripes
'360': otter
'361': skunk, polecat, wood pussy
'362': badger
'363': armadillo
'364': three-toed sloth, ai, Bradypus tridactylus
'365': orangutan, orang, orangutang, Pongo pygmaeus
'366': gorilla, Gorilla gorilla
'367': chimpanzee, chimp, Pan troglodytes
'368': gibbon, Hylobates lar
'369': siamang, Hylobates syndactylus, Symphalangus syndactylus
'370': guenon, guenon monkey
'371': patas, hussar monkey, Erythrocebus patas
'372': baboon
'373': macaque
'374': langur
'375': colobus, colobus monkey
'376': proboscis monkey, Nasalis larvatus
'377': marmoset
'378': capuchin, ringtail, Cebus capucinus
'379': howler monkey, howler
'380': titi, titi monkey
'381': spider monkey, Ateles geoffroyi
'382': squirrel monkey, Saimiri sciureus
'383': Madagascar cat, ring-tailed lemur, Lemur catta
'384': indri, indris, Indri indri, Indri brevicaudatus
'385': Indian elephant, Elephas maximus
'386': African elephant, Loxodonta africana
'387': lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens
'388': giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca
'389': barracouta, snoek
'390': eel
'391': coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus
kisutch
'392': rock beauty, Holocanthus tricolor
'393': anemone fish
'394': sturgeon
'395': gar, garfish, garpike, billfish, Lepisosteus osseus
'396': lionfish
'397': puffer, pufferfish, blowfish, globefish
'398': abacus
'399': abaya
'400': academic gown, academic robe, judge's robe
'401': accordion, piano accordion, squeeze box
'402': acoustic guitar
'403': aircraft carrier, carrier, flattop, attack aircraft carrier
'404': airliner
'405': airship, dirigible
'406': altar
'407': ambulance
'408': amphibian, amphibious vehicle
'409': analog clock
'410': apiary, bee house
'411': apron
'412': ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin,
dustbin, trash barrel, trash bin
'413': assault rifle, assault gun
'414': backpack, back pack, knapsack, packsack, rucksack, haversack
'415': bakery, bakeshop, bakehouse
'416': balance beam, beam
'417': balloon
'418': ballpoint, ballpoint pen, ballpen, Biro
'419': Band Aid
'420': banjo
'421': bannister, banister, balustrade, balusters, handrail
'422': barbell
'423': barber chair
'424': barbershop
'425': barn
'426': barometer
'427': barrel, cask
'428': barrow, garden cart, lawn cart, wheelbarrow
'429': baseball
'430': basketball
'431': bassinet
'432': bassoon
'433': bathing cap, swimming cap
'434': bath towel
'435': bathtub, bathing tub, bath, tub
'436': beach wagon, station wagon, wagon, estate car, beach waggon, station
waggon, waggon
'437': beacon, lighthouse, beacon light, pharos
'438': beaker
'439': bearskin, busby, shako
'440': beer bottle
'441': beer glass
'442': bell cote, bell cot
'443': bib
'444': bicycle-built-for-two, tandem bicycle, tandem
'445': bikini, two-piece
'446': binder, ring-binder
'447': binoculars, field glasses, opera glasses
'448': birdhouse
'449': boathouse
'450': bobsled, bobsleigh, bob
'451': bolo tie, bolo, bola tie, bola
'452': bonnet, poke bonnet
'453': bookcase
'454': bookshop, bookstore, bookstall
'455': bottlecap
'456': bow
'457': bow tie, bow-tie, bowtie
'458': brass, memorial tablet, plaque
'459': brassiere, bra, bandeau
'460': breakwater, groin, groyne, mole, bulwark, seawall, jetty
'461': breastplate, aegis, egis
'462': broom
'463': bucket, pail
'464': buckle
'465': bulletproof vest
'466': bullet train, bullet
'467': butcher shop, meat market
'468': cab, hack, taxi, taxicab
'469': caldron, cauldron
'470': candle, taper, wax light
'471': cannon
'472': canoe
'473': can opener, tin opener
'474': cardigan
'475': car mirror
'476': carousel, carrousel, merry-go-round, roundabout, whirligig
'477': carpenter's kit, tool kit
'478': carton
'479': car wheel
'480': cash machine, cash dispenser, automated teller machine, automatic
teller machine, automated teller, automatic teller, ATM
'481': cassette
'482': cassette player
'483': castle
'484': catamaran
'485': CD player
'486': cello, violoncello
'487': cellular telephone, cellular phone, cellphone, cell, mobile phone
'488': chain
'489': chainlink fence
'490': chain mail, ring mail, mail, chain armor, chain armour, ring armor,
ring armour
'491': chain saw, chainsaw
'492': chest
'493': chiffonier, commode
'494': chime, bell, gong
'495': china cabinet, china closet
'496': Christmas stocking
'497': church, church building
'498': cinema, movie theater, movie theatre, movie house, picture palace
'499': cleaver, meat cleaver, chopper
'500': cliff dwelling
'501': cloak
'502': clog, geta, patten, sabot
'503': cocktail shaker
'504': coffee mug
'505': coffeepot
'506': coil, spiral, volute, whorl, helix
'507': combination lock
'508': computer keyboard, keypad
'509': confectionery, confectionary, candy store
'510': container ship, containership, container vessel
'511': convertible
'512': corkscrew, bottle screw
'513': cornet, horn, trumpet, trump
'514': cowboy boot
'515': cowboy hat, ten-gallon hat
'516': cradle
'517': crane2
'518': crash helmet
'519': crate
'520': crib, cot
'521': Crock Pot
'522': croquet ball
'523': crutch
'524': cuirass
'525': dam, dike, dyke
'526': desk
'527': desktop computer
'528': dial telephone, dial phone
'529': diaper, nappy, napkin
'530': digital clock
'531': digital watch
'532': dining table, board
'533': dishrag, dishcloth
'534': dishwasher, dish washer, dishwashing machine
'535': disk brake, disc brake
'536': dock, dockage, docking facility
'537': dogsled, dog sled, dog sleigh
'538': dome
'539': doormat, welcome mat
'540': drilling platform, offshore rig
'541': drum, membranophone, tympan
'542': drumstick
'543': dumbbell
'544': Dutch oven
'545': electric fan, blower
'546': electric guitar
'547': electric locomotive
'548': entertainment center
'549': envelope
'550': espresso maker
'551': face powder
'552': feather boa, boa
'553': file, file cabinet, filing cabinet
'554': fireboat
'555': fire engine, fire truck
'556': fire screen, fireguard
'557': flagpole, flagstaff
'558': flute, transverse flute
'559': folding chair
'560': football helmet
'561': forklift
'562': fountain
'563': fountain pen
'564': four-poster
'565': freight car
'566': French horn, horn
'567': frying pan, frypan, skillet
'568': fur coat
'569': garbage truck, dustcart
'570': gasmask, respirator, gas helmet
'571': gas pump, gasoline pump, petrol pump, island dispenser
'572': goblet
'573': go-kart
'574': golf ball
'575': golfcart, golf cart
'576': gondola
'577': gong, tam-tam
'578': gown
'579': grand piano, grand
'580': greenhouse, nursery, glasshouse
'581': grille, radiator grille
'582': grocery store, grocery, food market, market
'583': guillotine
'584': hair slide
'585': hair spray
'586': half track
'587': hammer
'588': hamper
'589': hand blower, blow dryer, blow drier, hair dryer, hair drier
'590': hand-held computer, hand-held microcomputer
'591': handkerchief, hankie, hanky, hankey
'592': hard disc, hard disk, fixed disk
'593': harmonica, mouth organ, harp, mouth harp
'594': harp
'595': harvester, reaper
'596': hatchet
'597': holster
'598': home theater, home theatre
'599': honeycomb
'600': hook, claw
'601': hoopskirt, crinoline
'602': horizontal bar, high bar
'603': horse cart, horse-cart
'604': hourglass
'605': iPod
'606': iron, smoothing iron
'607': jack-o'-lantern
'608': jean, blue jean, denim
'609': jeep, landrover
'610': jersey, T-shirt, tee shirt
'611': jigsaw puzzle
'612': jinrikisha, ricksha, rickshaw
'613': joystick
'614': kimono
'615': knee pad
'616': knot
'617': lab coat, laboratory coat
'618': ladle
'619': lampshade, lamp shade
'620': laptop, laptop computer
'621': lawn mower, mower
'622': lens cap, lens cover
'623': letter opener, paper knife, paperknife
'624': library
'625': lifeboat
'626': lighter, light, igniter, ignitor
'627': limousine, limo
'628': liner, ocean liner
'629': lipstick, lip rouge
'630': Loafer
'631': lotion
'632': loudspeaker, speaker, speaker unit, loudspeaker system, speaker system
'633': loupe, jeweler's loupe
'634': lumbermill, sawmill
'635': magnetic compass
'636': mailbag, postbag
'637': mailbox, letter box
'638': maillot
'639': maillot, tank suit
'640': manhole cover
'641': maraca
'642': marimba, xylophone
'643': mask
'644': matchstick
'645': maypole
'646': maze, labyrinth
'647': measuring cup
'648': medicine chest, medicine cabinet
'649': megalith, megalithic structure
'650': microphone, mike
'651': microwave, microwave oven
'652': military uniform
'653': milk can
'654': minibus
'655': miniskirt, mini
'656': minivan
'657': missile
'658': mitten
'659': mixing bowl
'660': mobile home, manufactured home
'661': Model T
'662': modem
'663': monastery
'664': monitor
'665': moped
'666': mortar
'667': mortarboard
'668': mosque
'669': mosquito net
'670': motor scooter, scooter
'671': mountain bike, all-terrain bike, off-roader
'672': mountain tent
'673': mouse, computer mouse
'674': mousetrap
'675': moving van
'676': muzzle
'677': nail
'678': neck brace
'679': necklace
'680': nipple
'681': notebook, notebook computer
'682': obelisk
'683': oboe, hautboy, hautbois
'684': ocarina, sweet potato
'685': odometer, hodometer, mileometer, milometer
'686': oil filter
'687': organ, pipe organ
'688': oscilloscope, scope, cathode-ray oscilloscope, CRO
'689': overskirt
'690': oxcart
'691': oxygen mask
'692': packet
'693': paddle, boat paddle
'694': paddlewheel, paddle wheel
'695': padlock
'696': paintbrush
'697': pajama, pyjama, pj's, jammies
'698': palace
'699': panpipe, pandean pipe, syrinx
'700': paper towel
'701': parachute, chute
'702': parallel bars, bars
'703': park bench
'704': parking meter
'705': passenger car, coach, carriage
'706': patio, terrace
'707': pay-phone, pay-station
'708': pedestal, plinth, footstall
'709': pencil box, pencil case
'710': pencil sharpener
'711': perfume, essence
'712': Petri dish
'713': photocopier
'714': pick, plectrum, plectron
'715': pickelhaube
'716': picket fence, paling
'717': pickup, pickup truck
'718': pier
'719': piggy bank, penny bank
'720': pill bottle
'721': pillow
'722': ping-pong ball
'723': pinwheel
'724': pirate, pirate ship
'725': pitcher, ewer
'726': plane, carpenter's plane, woodworking plane
'727': planetarium
'728': plastic bag
'729': plate rack
'730': plow, plough
'731': plunger, plumber's helper
'732': Polaroid camera, Polaroid Land camera
'733': pole
'734': police van, police wagon, paddy wagon, patrol wagon, wagon, black
Maria
'735': poncho
'736': pool table, billiard table, snooker table
'737': pop bottle, soda bottle
'738': pot, flowerpot
'739': potter's wheel
'740': power drill
'741': prayer rug, prayer mat
'742': printer
'743': prison, prison house
'744': projectile, missile
'745': projector
'746': puck, hockey puck
'747': punching bag, punch bag, punching ball, punchball
'748': purse
'749': quill, quill pen
'750': quilt, comforter, comfort, puff
'751': racer, race car, racing car
'752': racket, racquet
'753': radiator
'754': radio, wireless
'755': radio telescope, radio reflector
'756': rain barrel
'757': recreational vehicle, RV, R.V.
'758': reel
'759': reflex camera
'760': refrigerator, icebox
'761': remote control, remote
'762': restaurant, eating house, eating place, eatery
'763': revolver, six-gun, six-shooter
'764': rifle
'765': rocking chair, rocker
'766': rotisserie
'767': rubber eraser, rubber, pencil eraser
'768': rugby ball
'769': rule, ruler
'770': running shoe
'771': safe
'772': safety pin
'773': saltshaker, salt shaker
'774': sandal
'775': sarong
'776': sax, saxophone
'777': scabbard
'778': scale, weighing machine
'779': school bus
'780': schooner
'781': scoreboard
'782': screen, CRT screen
'783': screw
'784': screwdriver
'785': seat belt, seatbelt
'786': sewing machine
'787': shield, buckler
'788': shoe shop, shoe-shop, shoe store
'789': shoji
'790': shopping basket
'791': shopping cart
'792': shovel
'793': shower cap
'794': shower curtain
'795': ski
'796': ski mask
'797': sleeping bag
'798': slide rule, slipstick
'799': sliding door
'800': slot, one-armed bandit
'801': snorkel
'802': snowmobile
'803': snowplow, snowplough
'804': soap dispenser
'805': soccer ball
'806': sock
'807': solar dish, solar collector, solar furnace
'808': sombrero
'809': soup bowl
'810': space bar
'811': space heater
'812': space shuttle
'813': spatula
'814': speedboat
'815': spider web, spider's web
'816': spindle
'817': sports car, sport car
'818': spotlight, spot
'819': stage
'820': steam locomotive
'821': steel arch bridge
'822': steel drum
'823': stethoscope
'824': stole
'825': stone wall
'826': stopwatch, stop watch
'827': stove
'828': strainer
'829': streetcar, tram, tramcar, trolley, trolley car
'830': stretcher
'831': studio couch, day bed
'832': stupa, tope
'833': submarine, pigboat, sub, U-boat
'834': suit, suit of clothes
'835': sundial
'836': sunglass
'837': sunglasses, dark glasses, shades
'838': sunscreen, sunblock, sun blocker
'839': suspension bridge
'840': swab, swob, mop
'841': sweatshirt
'842': swimming trunks, bathing trunks
'843': swing
'844': switch, electric switch, electrical switch
'845': syringe
'846': table lamp
'847': tank, army tank, armored combat vehicle, armoured combat vehicle
'848': tape player
'849': teapot
'850': teddy, teddy bear
'851': television, television system
'852': tennis ball
'853': thatch, thatched roof
'854': theater curtain, theatre curtain
'855': thimble
'856': thresher, thrasher, threshing machine
'857': throne
'858': tile roof
'859': toaster
'860': tobacco shop, tobacconist shop, tobacconist
'861': toilet seat
'862': torch
'863': totem pole
'864': tow truck, tow car, wrecker
'865': toyshop
'866': tractor
'867': trailer truck, tractor trailer, trucking rig, rig, articulated lorry,
semi
'868': tray
'869': trench coat
'870': tricycle, trike, velocipede
'871': trimaran
'872': tripod
'873': triumphal arch
'874': trolleybus, trolley coach, trackless trolley
'875': trombone
'876': tub, vat
'877': turnstile
'878': typewriter keyboard
'879': umbrella
'880': unicycle, monocycle
'881': upright, upright piano
'882': vacuum, vacuum cleaner
'883': vase
'884': vault
'885': velvet
'886': vending machine
'887': vestment
'888': viaduct
'889': violin, fiddle
'890': volleyball
'891': waffle iron
'892': wall clock
'893': wallet, billfold, notecase, pocketbook
'894': wardrobe, closet, press
'895': warplane, military plane
'896': washbasin, handbasin, washbowl, lavabo, wash-hand basin
'897': washer, automatic washer, washing machine
'898': water bottle
'899': water jug
'900': water tower
'901': whiskey jug
'902': whistle
'903': wig
'904': window screen
'905': window shade
'906': Windsor tie
'907': wine bottle
'908': wing
'909': wok
'910': wooden spoon
'911': wool, woolen, woollen
'912': worm fence, snake fence, snake-rail fence, Virginia fence
'913': wreck
'914': yawl
'915': yurt
'916': web site, website, internet site, site
'917': comic book
'918': crossword puzzle, crossword
'919': street sign
'920': traffic light, traffic signal, stoplight
'921': book jacket, dust cover, dust jacket, dust wrapper
'922': menu
'923': plate
'924': guacamole
'925': consomme
'926': hot pot, hotpot
'927': trifle
'928': ice cream, icecream
'929': ice lolly, lolly, lollipop, popsicle
'930': French loaf
'931': bagel, beigel
'932': pretzel
'933': cheeseburger
'934': hotdog, hot dog, red hot
'935': mashed potato
'936': head cabbage
'937': broccoli
'938': cauliflower
'939': zucchini, courgette
'940': spaghetti squash
'941': acorn squash
'942': butternut squash
'943': cucumber, cuke
'944': artichoke, globe artichoke
'945': bell pepper
'946': cardoon
'947': mushroom
'948': Granny Smith
'949': strawberry
'950': orange
'951': lemon
'952': fig
'953': pineapple, ananas
'954': banana
'955': jackfruit, jak, jack
'956': custard apple
'957': pomegranate
'958': hay
'959': carbonara
'960': chocolate sauce, chocolate syrup
'961': dough
'962': meat loaf, meatloaf
'963': pizza, pizza pie
'964': potpie
'965': burrito
'966': red wine
'967': espresso
'968': cup
'969': eggnog
'970': alp
'971': bubble
'972': cliff, drop, drop-off
'973': coral reef
'974': geyser
'975': lakeside, lakeshore
'976': promontory, headland, head, foreland
'977': sandbar, sand bar
'978': seashore, coast, seacoast, sea-coast
'979': valley, vale
'980': volcano
'981': ballplayer, baseball player
'982': groom, bridegroom
'983': scuba diver
'984': rapeseed
'985': daisy
'986': yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus,
Cypripedium parviflorum
'987': corn
'988': acorn
'989': hip, rose hip, rosehip
'990': buckeye, horse chestnut, conker
'991': coral fungus
'992': agaric
'993': gyromitra
'994': stinkhorn, carrion fungus
'995': earthstar
'996': hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola
frondosa
'997': bolete
'998': ear, spike, capitulum
'999': toilet tissue, toilet paper, bathroom tissue
- name: lexicon
sequence: string
- name: id
dtype: int64
splits:
- name: validation
num_bytes: 406246742.0
num_examples: 3000
download_size: 398667087
dataset_size: 406246742.0
---
# Dataset Card for "Imagenet1k_sample_validation"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 39,285 | [
[
-0.041015625,
-0.009307861328125,
0.0001685619354248047,
0.023468017578125,
-0.0295562744140625,
-0.019866943359375,
0.030181884765625,
-0.007457733154296875,
0.04644775390625,
0.04083251953125,
-0.06378173828125,
-0.0599365234375,
-0.030731201171875,
-0.008... |
maximedb/sick_nl | 2023-04-25T10:19:43.000Z | [
"task_categories:text-classification",
"size_categories:1K<n<10K",
"language:nl",
"license:mit",
"region:us"
] | maximedb | null | null | 0 | 11 | 2023-02-16T07:44:25 | ---
dataset_info:
features:
- name: pair_ID
dtype: int64
- name: sentence_A
dtype: string
- name: sentence_B
dtype: string
- name: entailment_label
dtype: string
- name: relatedness_score
dtype: float64
- name: entailment_AB
dtype: string
- name: entailment_BA
dtype: string
- name: sentence_A_original
dtype: string
- name: sentence_B_original
dtype: string
- name: sentence_A_dataset
dtype: string
- name: sentence_B_dataset
dtype: string
- name: SemEval_set
dtype: string
- name: label
dtype: int64
- name: label_seq2seq
dtype: string
splits:
- name: train
num_bytes: 1359887
num_examples: 4439
- name: validation
num_bytes: 153417
num_examples: 495
- name: test
num_bytes: 1496660
num_examples: 4906
download_size: 822658
dataset_size: 3009964
license: mit
task_categories:
- text-classification
language:
- nl
pretty_name: SICK-NL
size_categories:
- 1K<n<10K
---
## Dataset Description
- **Homepage:** https://github.com/gijswijnholds/sick_nl
- **Repository:** https://github.com/gijswijnholds/sick_nl
- **Paper:** https://aclanthology.org/2021.eacl-main.126/
- **Point of Contact:** [Gijs Wijnholds](mailto:gijswijnholds@gmail.com)
### Dataset Summary
An automatically translated, manually corrected translation of the SICK dataset of [Marelli et al. 2014](https://www.aclweb.org/anthology/L14-1314), intended to boost research in Dutch NLP.
### Languages
The dataset is in Dutch.
## Dataset Structure
### Data Fields
- pair_ID: sentence pair ID
- sentence_A: sentence A
- sentence_B: sentence B
- label: textual entailment gold label: entailment (0), neutral (1) or contradiction (2)
- relatedness_score: semantic relatedness gold score (on a 1-5 continuous scale)
- entailment_AB: entailment for the A-B order (A_neutral_B, A_entails_B, or A_contradicts_B)
- entailment_BA: entailment for the B-A order (B_neutral_A, B_entails_A, or B_contradicts_A)
- sentence_A_original: original sentence from which sentence A is derived
- sentence_B_original: original sentence from which sentence B is derived
- sentence_A_dataset: dataset from which the original sentence A was extracted (FLICKR vs. SEMEVAL)
- sentence_B_dataset: dataset from which the original sentence B was extracted (FLICKR vs. SEMEVAL)
### Data Splits
Train Trial Test
4439 495 4906
## Dataset Creation
The dataset was created by first automatically translating all sentences, then by manually correcting any translation errors. This guarantees naturality of the examples while aligning the relatedness scores and entailment labels. Since the data IDs are preserved the dataset is fully aligned on the sentence level.
## Additional Information
### Licensing Information
This dataset falls under an MIT License.
### Citation Information
```
@inproceedings{wijnholds-etal-2021-sicknl,
title = "SICK-NL: A Dataset for Dutch Natural Language Inference",
author = "Wijnholds, Gijs and Moortgat, Michael",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.eacl-main.126/",
}
```
### Contributions
Thanks to [@maximedb](https://huggingface.co/maximedb) for adding this dataset. | 3,439 | [
[
-0.0086212158203125,
-0.056732177734375,
0.0171966552734375,
0.0321044921875,
-0.0279388427734375,
-0.04534912109375,
-0.016357421875,
-0.048065185546875,
0.0491943359375,
0.04266357421875,
-0.0308074951171875,
-0.052734375,
-0.043243408203125,
0.05535888671... |
t0mmy/livedoor_news_corpus | 2023-03-12T02:25:37.000Z | [
"task_categories:text-classification",
"size_categories:1K<n<10K",
"language:ja",
"license:cc",
"region:us"
] | t0mmy | This corpus is from news stories in “livedoor news” administered by NHN Japan and only the following ones that are governed by Creative Commons license were collected and had as many HTML tags as possible deleted. | null | 1 | 11 | 2023-02-21T09:02:23 | ---
license: cc
task_categories:
- text-classification
language:
- ja
pretty_name: livedoor News Corpus
size_categories:
- 1K<n<10K
---
# Dataset Card for "livedoor_news_corpus"
## Dataset Description
- **Homepage:** [ダウンロード - 株式会社ロンウイット](http://www.rondhuit.com/download.html#ldcc)
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** [RONDHUIT](mailto:sales@rondhuit.com)
### Dataset Summary
The livedoor News Corpus is a collection of 7k human-written Japanese news stories.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The language in the dataset is Japanese. The BCP-47 code for Japanese is ja.
## Dataset Structure
### Data Instances
For each instance, there is a string for the URL, a datetime for the date, a string for the title, a string for the text, and an integer for the label.
```
{'url': 'http://news.livedoor.com/article/detail/6601535/',
'date': '2012-05-28T12:55:00+0900',
'title': 'NTTドコモ、2012夏モデル新商品内覧会を東京・名古屋・大阪で開催！DCMXおよびプレミアステージ会員向け',
'text': '2012夏モデル新商品内覧会が開催！ \n\nNTTドコモは28日、この夏以降に発売予定の新商品を発売前に体験できる「2012 夏モデル新商品内覧会」を東京や名古屋、大阪にてDCMX会員およびプレミアステージ会員（ドコモプレミアクラブ）を対象に実施することをお知らせしています。\n\n事前お申込みは不要で、当日、入場の際にDCMXカードもしくはドコミプレミアクラブ・サイト画面を提示することで、入場できます。\n\nまた、1人の対象者がいれば、知り合いや友だちを連れていっても大丈夫とのことです。なお、DCMX mini会員は対象外となるということです。\n\n開催日時および開催会場は、以下の通りです。ただし、時間帯によっては混雑のために入場制限をする場合があるとのことですので、ご注意ください。\n\n【開催日】\n・東京会場\n2012年6月8日（金）〜10日（日）\n・名古屋会場\n2012年6月15日（金）〜17日（日）\n・大阪会場\n2012年6月16日（土）〜17日（日）\n\n※時間帯によっては混雑のため、入場制限させていただく場合があります。あらかじめご了承願います。\n※お連れ様は何名でもご来場いただけます。\n※会場までの交通費等はお客様ご負担となります。\n※ご来場の際は、公共交通機関をご利用ください。\n\n【東京会場】\n■会場\n東京ドームシティ プリズムホール 1F\n大好評の各機種のメーカー担当者によるプレゼンテーション、スマートフォン講座の他、20周年の感謝の気持ちを込めて、約60機種の歴代ケータイの展示や、歴代ドコモダケ展示など、特別企画も盛りだくさん！ご家族、お友達をお誘いの上、是非ご来場ください。\n\nステージスケジュールは6月1日（金）公開予定！\n■日時\n2012年6月8日（金）午後5：00〜午後9：00\n※最終入場時間：午後8：30\n2011年6月9日（土）・10日（日）午前10：30〜午後6：00\n※最終入場時間：午後5：30\n\n※途中入場可\n※開場時間にご注意ください。\n※当日の様子を取材しホームページ等に掲載する場合があります。なお、当日取材させていただいた画像、コメントなどの肖像権は弊社に帰属するものとさせていただきます。\n■混雑状況\n当日の混雑状況についてご確認いただけます。\n詳しくはこちら\n■住所\n東京都文京区後楽1-3-61\n東京ドームシティ プリズムホール 1F\n■交通アクセス\n・JR中央線・総武線・都営三田線「水道橋駅」徒歩約1分\n・東京メトロ丸ノ内線・南北線「後楽園駅」徒歩約3分\n・都営大江戸線「春日駅」徒歩約5分\n\n\n【名古屋会場】\n■会場\n栄ガスビル5F ガスホール\nスマートフォンのステージイベントを実施予定！モバイルアスキー・アスキードットPC編集部presentsで定番のアプリからおすすめの人気アプリなどを紹介します。\n\nステージスケジュールは6月1日（金）公開予定！\n\nDCMXのカードをご提示いただいた方に抽選で粗品をプレゼントいたします。DCMX会員の皆様は、是非DCMXのカードをご持参ください。\n※6月15日（金）は内覧会は開催されますが、ステージはございません。\n■日時\n2012年6月15日（金）午後6：00〜午後9：00\n※最終入場時間：午後8：30\n2012年6月16日（土）・17日（日）午前11：00〜午後6：00\n※最終入場時間：午後5：30\n\n※途中入場可\n※開催時間にご注意ください。\n■住所\n愛知県名古屋市中区栄3-15-33\n栄ガスホール 5F 栄ガスホール\n■交通アクセス\n・地下鉄東山線・名城線「栄駅」サカエチカ6番出口より徒歩約5分\n・地下鉄名城線「矢場町駅」6番出口より徒歩約2分\n\n\n【大阪会場】\n■会場\nハービスOSAKA B2F ハービスHALL\nスペシャルステージを実施予定！ 各機種のメーカー担当者によるプレゼンテーションの他、メーカー担当者が一堂に会する「スマートフォンサミット」、その他お楽しみ企画もあるよ！\nステージスケジュールは6月1日（金）公開予定！\n\n■日時\n2012年6月16日（土）・17日（日）午前11：00〜午後6：00\n※最終入場時間：午後5：30\n※途中入場可\n※当日の様子を取材しホームページ等に掲載する場合があります。なお、当日取材させていただいた画像、コメントなどの肖像権は弊社に帰属するものとさせていただきます。\n■住所\n大阪府大阪市北区梅田2-5-25\nハービスOSAKA B2F ハービスHALL\n■交通アクセス\n・阪神電車「梅田駅」西改札より徒歩約6分\n・JR線「大阪駅」桜橋口より徒歩約7分\n・地下鉄御堂筋線「梅田駅」南改札より徒歩約10分\n・阪急電車「梅田駅」より徒歩約15分\n\n記事執筆：memn0ck\n\n■関連リンク\n・エスマックス（S-MAX）\n・エスマックス（S-MAX） smaxjp on Twitter\n・DCMX｜ドコモのケータイクレジット\n',
'label': 6}
```
### Data Fields
- `url`: a string that URL
- `date`: a datetime that date
- `title`: a string that title
- `text`: a string that text
- `label`: an integer whose value may be either 0, indicating that category is Topic News, 1, indicating that category is Sports Watch, 2, indicating that category is IT Life Hack, 3, indicating that category is Appliance Channel, 4, indicating that category is MOVIE ENTER, 5, indicating that category is Single Woman Report, 6, indicating that category is Smax, 7, indicating that category is livedoor HOMME, 8, indicating that category is Peachy.
### Data Splits
The livedoor News Corpus has 1 split: *train*.
| Dataset Split | Number of Instances in Split |
| ------------- | ---------------------------- |
| Train | 7,367 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The livedoor News Corpus was developed by [RONDHUIT](https://www.rondhuit.com/en.html).
### Licensing Information
The livedoor News Corpus is licensed under a [Creative Commons Attribution-NoDerivs 2.1 Japan License](https://creativecommons.org/licenses/by-nd/2.1/jp/)
### Citation Information
```
@misc{livedoornewscorpus,
title={livedoor News Corpus},
author={RONDHUIT},
year={2012},
howpublished={\url{http://www.rondhuit.com/download.html#ldcc}}
}
```
### Contributions
Thanks to [@rondhuit](https://github.com/RONDHUIT) for adding this dataset. | 5,258 | [
[
-0.06292724609375,
-0.049163818359375,
0.03717041015625,
0.01219940185546875,
-0.04351806640625,
-0.009368896484375,
-0.019134521484375,
-0.038543701171875,
0.051849365234375,
0.0341796875,
-0.05859375,
-0.046875,
-0.033050537109375,
0.010772705078125,
-... |
UKPLab/insincere-questions | 2023-02-23T13:48:27.000Z | [
"region:us"
] | UKPLab | null | null | 0 | 11 | 2023-02-23T13:43:00 | This is a version of the Quora Insincere Questions Classification (https://www.kaggle.com/c/quora-insincere-questions-classification) task with a validation split. | 163 | [
[
-0.0216522216796875,
-0.06671142578125,
0.0185546875,
0.005977630615234375,
-0.01371002197265625,
0.02783203125,
0.0203704833984375,
-0.0350341796875,
0.016021728515625,
0.07275390625,
-0.05804443359375,
-0.0002765655517578125,
-0.0106964111328125,
-0.000992... |
wbbbbb/pclue | 2023-02-25T08:20:02.000Z | [
"task_categories:text-generation",
"language:zh",
"license:apache-2.0",
"region:us"
] | wbbbbb | https://github.com/CLUEbenchmark/pCLUE | https://github.com/CLUEbenchmark/pCLUE | 7 | 11 | 2023-02-25T02:39:00 | ---
license: apache-2.0
task_categories:
- text-generation
language:
- zh
---
# pCLUE
pCLUE: Large-scale Prompt-based Dataset for Multi-task and Zero-shot Learning in Chinese
pCLUE：基于提示的大规模预训练数据集，用于多任务学习和零样本学习
### 已转化数据集
数据量： 120万训练数据，73个Prompt
1. 训练集 train.json: 1,200,705
2. 验证集 dev.json: 100,000
3. 公开测试集 test_public.json: 129,556
4. 测试集 test.json: 250,461
具体数据，见：./datasets
### 目前已经有包含9个数据集：
1.单分类tnews
2.单分类iflytek
3.自然语言推理ocnli
4.语义匹配afqmc
5.指代消解-cluewsc2020
6.关键词识别-csl
7.阅读理解-自由式c3
8.阅读理解-抽取式cmrc2018
9.阅读理解-成语填空chid
### 字段说明及评价标准：
input:模型的输入
target:模型的输出
type:任务类型，阅读理解(mrc),分类(classify)，生成(generate)，自然语言推理(nli)
评价标准：阅读理解(em),分类(acc)，生成(em)，自然语言推理(acc)
answer_choices:选项（只有分类、推理类任务有）
### 提交样例：
见resources/promptclue_submit_examples。只需提交一个文件，每行是一个json，如：{"target": "2000万元"}
### 示例：
{"input": "哪个类别最好的描述了这篇新闻？扣篮王拉文：精彩暴扣表演！炸\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "电竞", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "你会把这个描述推荐给哪方面的人？银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿快来施放属于你的寒冰魔法吧特殊效果雪花缓缓从上方飘落，手指触碰之处有冰魔法出现爱莎女王脱掉了封印魔法她的手套，在冰雪天地中建造了属于她一个人的辉煌宫殿。安娜中了冰魔法需要真爱之吻才能获救，最终姐妹二人齐心揭穿了异国王子的阴谋拯救了阿伦戴尔。解锁方法随意滑动屏幕一定距离后解锁要是觉得好玩，记得推荐给好朋友哦,,1.新增多张精美冰雪奇缘壁纸2.增加冰雪图钉，锁定当前壁纸功能3.内存，减小电量消耗\n答案：", "target": "休闲益智", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "阅读以下文章，并选择一个合适的成语。文章：\n赵宝刚导演表示，当看到温家宝总理在灾区安慰失去亲人__的孩子时，他再也控制不住自己的感情，不禁潸然泪下。他非常关心灾区的孤儿，目前正计划为孩子们做一些更有意义的事情。当记者问到是否会考虑日后拍一部地震题材的影片时，赵宝刚导演则明确表示自己更愿意为灾区做一些实事，目前正在积极了解灾区儿童的需要，为下一步援助工作做准备。\n 候选成语：忧心忡忡，提心吊胆，后顾之忧，土豪劣绅，叫苦不迭，用武之地，无计可施，明眸皓齿，孤立无援，步步为营。答案是：", "target": "孤立无援", "answer_choices": ["忧心忡忡", "提心吊胆", "后顾之忧", "土豪劣绅", "叫苦不迭", "用武之地", "无计可施", "明眸皓齿", "孤立无援", "步步为营"], "type": "mrc"}
{"input": "这是关于哪方面的新闻？黄埔军校老师有哪些？\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "军事", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "这个是关于哪方面的App应用程序的描述？银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿“魅爱同城美女主动视频陪聊神器，女神绝密私照，一对一视频畅聊，保护你的私密。清纯的萌妹子、火辣的舞女郎，惊艳的时装秀，浪漫的午夜邂逅，伴你告别寂寞和美女主播视频聊天、交友、热舞零距离互动。让你随时随地享受偶遇的激情与惊喜与网红视频网红主播与你在线视频交友，浪漫邂逅。生活动态圈高颜值女神用短视频和照片与你分享生活中的点滴。\n答案：", "target": "约会社交", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "阅读理解：\n有一次，有人问马克·吐温是否记得他第一次是怎样挣到钱的。他想了很久，然后说：“对，我还记得很清楚，那是我在小学读书的时候。那时，小学生们都不尊重自己的老师，而且不爱惜学校的财产，经常弄坏桌椅。所以我们学校就定了一条规则，哪个学生用铅笔或小刀弄坏了桌椅，他就得在全校学生面前挨老师的打，或者交五元罚款。有一天，我弄坏了我的书桌，只好回家对父亲说，我违反了学校的规定，要么罚五元，要么在全校学生面前受到挨打的处分。父亲说当着全校学生的面挨打真是太丢脸了，他答应给我五块钱，让我交给学校。但是在给我这五块钱之前，他把我带到楼上，狠狠地打了我一顿。我想，既然我已经挨过一顿打了，那就干脆当着全校学生的面再挨一顿，这样就可以把那五块钱留下来。我真的这样做了，那就是我第一次挣到的钱。” \n问：父亲为什么给马克·吐温钱? 选项：喜欢他，奖励他，怕丢脸，感谢他\n答案：", "target": "怕丢脸", "type": "mrc", "answer_choices": ["喜欢他", "奖励他", "怕丢脸", "感谢他"]}
{"input": "“全面加强教师特别是农村教师培训,鼓励大学生、师范生到基层、农村任教”根据前面的段落，以下是否是真的“农村教师的培训需要特别重视”？是的,不是,或也许？\n答案：", "target": "是的", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "给定“国民经济保持较快增长”我们应该假定“国民经济一个月内还会保持快速增长”是真的吗？是的,不是,或也许？\n答案：", "target": "也许", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "这个是关于哪方面的App应用程序的描述？银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿移动吧是移动官方面向青海移动用户推出的移动智能终端网上营业厅。新版的移动吧为用户提供方便快捷的账单查询、业务办理、积分查询、通讯录等功能。随时随地尽享青海移动的贴心服务，方便触手可及。查询更丰富直观准确、消费透明充值更优惠专享优惠、充值赠费办理更便捷套餐流量、随时办理好友更亲密相互关注、贴心关怀活动更精彩活动不停、优惠不断更新内容1修复已知Bug；2优化客户端访问速度；3提升活动体验，丰富奖励资源。\n答案：", "target": "工具", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "足三两（）是麦当劳推出的一种汉堡包，为继巨无霸后的另一招牌食品。英文名称的意思是「四分之一磅」，因为牛肉重量大约等如四分之一磅（烹调前计），而四分之一磅大约等于三两重，故在香港被称为「足-{}-三两」。在麦当劳于1975年进入香港市场时，Quarter Pounder曾被命名为「大汉-{}-堡」，而Quarter Pounder with Cheese则被命名为「大芝-{}-士汉-{}-堡」，但于1980年代后停售。2000年代初，曾经作为推广产品重新命名为「足-{}-三两」（或写作足-{}-三両），但推广期后便继续停售。直至2007年起，麦当劳在香港推出「Double足-{}-三两」（Double Quarter Pounder，即是双重份量的足-{}-三两）作为MacTonight套餐，于香港时间每晚21:00至翌日凌晨04:00间供应。由于反应理想，香港麦当劳于2009年将其发售时段提早至上午11时开始，并重新引入常规版的「足-{}-三两」作为长期发售的项目。Double足-{}-三两已于2017年初停售，常规版足-{}-三两亦于同年3月9日起停售。事实上，在香港售卖的「足-{}-三两」实际重量只有100克。香港麦当劳的餐牌上足-{}-三两及Double足-{}-三两都会以小字体加上「烹调前」标签，以符合香港海关《商品说明条例》的规定。一个正常的足三两，包括有四分之一磅（113.4克）牛肉（烹调前计）、两块芝麻面包、酸瓜、茄酱及生洋葱，而很多时候足三两也会有一块芝士。\n 从上面的段落中，根据一个合理的答案：麦当劳\n那么问题可能是：", "target": "足三两是哪个品牌的招牌食品之一？", "type": "mrc"}
{"input": "“切实转变工作作风”根据前面的段落，以下是否是真的“这是公文话语”？是的,不是,或也许？\n答案：", "target": "是的", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "“逐步实行中等职业教育免费,今年先从农村家庭经济困难学生和涉农专业做起”记住上面的文字,考虑:“后年就能够全面实现中等职业教育免费”这是总是,绝不,或有时正确的？\n答案：", "target": "有时", "answer_choices": ["总是", "绝不", "有时"], "type": "nli"}
{"input": "阅读下列论文的摘要，然后生成这篇摘要的多个关键词。摘要：通过对泥河湾盆地43条剖面和6个钻孔晚新生代地层和微体古生物(介形类和有孔虫)的调查研究,发现非常丰富的介形类,计26属70余种,有孔虫4属4种,其中介形类自下而上可明显地划分为5个组合带:(1)Potamocyprisplana-Candoniella-Ilyocypris组合带;(2)Leucocythere-Ilyocypris-Candoniella组合带;(3)Leucocythere-Cytherissa-Limnocythere组合带;(4)Ilyocypris-Limnocythereflexa-Limnocytheredubiosa组合带;(5)Limnocytheredubiosa-Limnocytheresancti-Patricii-Ilyocypris组合带.按以上5个介形类组合带的分布,第1组合带及所含地层红崖村组和石匣组的时代为上新世;第2～4组合带及所含地层泥河湾组的时代为早更新世;第5组合带为中-晚更新世,分布于虎头梁组和许家窑组,虎头梁组置中更新世为宜,许家窑组为晚更新世.根据5个介形类组合带和有孔虫的分布及介形类的始现、繁盛、兴衰的演替特征,对泥河湾古湖和盆地的形成经历了上新世的起始,早更新世早期的扩展,中、晚期稳定、发展、湖面最大,中更新世向西部退缩和晚更新世消亡、桑干河水系形成五个发展阶段的演化进行了探讨.。摘要的关键词有这些：\n答案：", "target": "介形类，晚新生代，环境演化，生物地层", "answer_choices": "", "type": "generate"}
{"input": "这个App应用程序的描述会出现在哪个栏目？•只需随身携带手机即可随时了解您步行、跑步和骑车的运动情况。达成健身目标•设定时长或步数目标，并了解自己的进度。•获得根据健身效果提供的运动目标建议。全面掌握健身情况•将第三方设备和应用与Google健身关联后，您就可以在一个地方集中查看您的所有健身数据。随时随地使用•兼容所有AndroidWer设备。•还可以通过浏览器www.google.com/fit和平板电脑使用Google健身。更新内容提升体验，修复部分问题。\n选项：银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿\n答案：", "target": "运动健身", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "这个是关于哪方面的App应用程序的描述？银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿神秘又惊喜的万圣节到啦快来宝宝超市挑选你最爱的南瓜灯和面具吧还可以挑个礼服画个妆，打造超炫的万圣节造型呢和奇奇一起学会在超市购物，成为妈妈购物的好帮手吧丰富商品水果，蔬菜，玩具，零食…各种商品一应俱全模拟真实超市购物的场景，让宝宝体验超市购物的乐趣。根据清单购物你能帮妈妈买到清单上的东西吗对照清单购买需要的东西，让孩子有目的性的逛超市，帮宝宝树立正确的消费观。模拟结账别忘记结账哟~所有商品一共8元，付了10元，该找回多少钱呢，你能帮奇奇算一算吗丰富小游戏鱼缸捞鱼、搭配你喜欢的蛋糕、帮试妆员化上美丽的妆…丰富趣味小游戏，乐趣无穷宝宝巴士以孩子的兴趣启蒙为出发点，从健康、语言、社会、科学、艺术五大领域关注幼儿成长，吸取蒙氏教育精髓，根据幼儿不同年龄段左右脑发育、敏感期特点和学习重点来设计产品，打造“年龄+能力”的多元化产品体系。让孩子在游戏中独立思考，自由学习，享受探索世界的乐趣。宝宝巴士儿童早教pp，众多儿童早教产品的一致选择，孩子从小学宝宝巴士儿歌，贝瓦儿歌，儿歌点点，宝宝树，小伴龙，贝乐虎儿歌，咔哒故事，伴鱼绘本，宝宝手工零食，宝宝时尚设计师等使用者的一致推荐。设计理念宝宝巴士BbyBus,专注启蒙，而不仅仅是教育。我们专注于启发，而不只是学习。我们专注于能力培养，而不只是单一认知。我们专注于寓教于乐，而不是填鸭式教学。宝宝巴士，快乐启蒙全球3.5亿家庭用户的早教首选，您身边的幼儿教育专家搜索宝宝巴士，就可以下载宝宝巴士的所有早教APP了哦~欢迎联系微信宝宝巴士微博@宝宝巴士官网http//www.bbybus.com邮箱cn@bbybus.com更新内容不放过任何可以提升体验的地方，优化细节，让游戏体验更上一层楼贴心的小bug修复，提升稳定性和流畅度，畅玩无压力搜索宝宝巴士，就可以下载宝宝巴士的所有早教APP了哦~欢迎加入宝宝巴士官方Q群288190979，一起为孩子做更多更好的产品。\n答案：", "target": "亲子儿童", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "参考下面的段落，回答下列问题：\n段落：因吊钟的花朵通常在农历新年前后开花，故英文又名为Chinese New Year Flower，意即中国新年花。在清代中叶开始已有吊钟作为年花的习俗，取其「金钟一响，黄金万两」的吉兆，同时吊钟花的花朵都是生长在枝顶上，亦有高中科举之寓意，古时百姓因希望子弟能高中科举，就砍伐吊钟花带回家作为年花。不过近年因人们觉“吊钟”和“吊终”谐音，不吉利，所以较少人以吊钟作为年花。吊钟是一种落叶或半常绿灌木，可高约7米，但常高3米。树皮呈灰黄色，多分枝，小枝呈淡褐色。叶长圆形或倒卵状长圆形，先端渐尖，基部渐狭而成短柄，常密集生于枝顶，互生，革质，表面绿色而背面淡绿色，长5－10厘米，阔2－4厘米，全缘或顶部疏生细齿，叶两面无毛，侧脉6－7对，中脉两面清晰呈羽状伸出，网脉两面清晰，叶短柄长约5－20厘米，灰黄色呈圆柱状无毛。花为伞房花序顶生，花粉红色或红色，常5－8朵，下垂呈钟型，从枝顶覆瓦状排列的红色大苞片内生出，苞片长圆形或长方形，膜质，花梗绿色无毛，长约1.5－2厘米，花萼5裂，披针形先端披纤毛，长约2－4厘米，花冠呈宽钟状，口部5裂，裂片长约1－1.2厘米，裂片钝圆，轻微反卷白色，雄蕊8枚，雌蕊1枚，雌蕊较雄蕊长。果为蒴果，椭圆形无毛，淡黄色，具5梭，长约8－12厘米，果柄直立粗壮，长约3－5厘米。种子有3－5角或翅。喜温暖湿润，日光充足，土壤肥沃含腐殖质及排水良好的土壤。可以使用播种、扦插法及压条法繁殖。\n问题：吊钟花如何进行繁殖？\n答案：", "target": "播种、扦插法及压条法", "type": "mrc"}
{"input": "从医院打完针、开了药回来。母亲就赶到单位去上班了。走前，她把我托付给禾寡妇（候选词），请她(代词)关照我。。上面的句子中，代词“她”指代的是“禾寡妇”吗？选项：是的，不是。答案：", "target": "是的", "type": "anaphora_resolution", "answer_choices": ["是的", "不是"]}
{"input": "《1997年郡尉职权法案》（）于1997年生效，是一项英国国会法案，来厘订大不列颠委任的郡尉（Lord Lieutenant）所管辖的地区。根据《1888年地方政府法案》，郡尉是被委派到每一个郡。可是，这个法案所定义的区域混杂了新的行政郡及郡的自治区。实际上，影响很微小，因为只有少数行政郡的边界跟原来的不一样。直到1965年大伦敦及亨廷登-彼得伯勒郡的成立，导致米德尔塞克斯郡尉办公室、伦敦郡郡尉办公室、亨廷登郡郡尉办公室被废除，取而代之就是大伦敦郡尉及亨廷登-彼得伯勒郡尉。1974年，英格兰及威尔斯内的行政郡及郡自治区被废除。一项大型改革也同时推行。所有郡尉辖区都被划分为都会郡和非都会郡。而1973年《苏格兰地方政府法案》则不跟从新的苏格兰地区来厘订郡尉辖区，反而从传统郡中拼合起来。因此，两者结合导致产生出来的郡尉辖区完全不跟从原有的郡。大部分这些郡尉辖区都没有留下来。在1990年代中期的英国地方政府改革中，很多非都会郡都开始重组成为单一管理区。苏格兰及威尔斯的地方政府过渡成为只由单一管理区所组成。这个时候开始草拟这个法案的计划，把郡尉辖区从地方政府再次分出来。虽然法案没有使用这个计划，但这些地方成了英格兰的名誉郡。\n 参考上述上下文，改革推行后，所有郡尉辖区被划分为什么？\n答案：", "target": "都会郡和非都会郡", "type": "mrc"}
{"input": "香港2004年继去年七一游行后再次经历了巨大政治争议，4月全国人民代表大会常务委员会第二次行使权力解释基本法，并否决了0708年双普选。5月，商业电台多名著名节目主持人指受到压力相继暂停节目，发生了「商台名嘴封咪事件」。7月1日，仍有数以十万计市民参与七一游行表达争取民主诉求。9月，第三届立法会选举刷新了历届投票纪录，有178万多人投票（投票率55.64%）。经济方面，去年发生沙士事件后情况逐渐改善，失业率下跌至2004年第四季的6.5%，是近三年以来的低位，年内本地生产总值增长8.1%，是自1987年以来的第二快增长，历时68个月的通缩终于结束，经济复苏主要受惠于东亚、欧美国等主要市场的强劲需求，以及中国内地对外贸易畅旺和内部需求殷切所带动。然而去年沙士期间，带来经济下滑以及增加开支，政府账目录得赤字401亿。下列节庆，如无注明，均是香港的公众假期，同时亦是法定假日（俗称劳工假期）。有 # 号者，不是公众假期或法定假日（除非适逢星期日或其它假期），但在商业炒作下，市面上有一定节庆气氛，传媒亦对其活动有所报导。详情可参看香港节日与公众假期。\n 从上面的段落中，根据一个合理的答案：受惠于东亚、欧美国等主要市场的强劲需求，以及中国内地对外贸易畅旺和内部需求殷切所带动。\n那么问题可能是：", "target": "香港2004年经济复苏的原因是什么？", "type": "mrc"}
{"input": "这是关于哪方面的新闻： 故事,文化,娱乐,体育,财经,房产,汽车,教育,科技,军事,旅游,国际,股票,农业,游戏？首次承认落后，美媒披露中国高超音速导弹技术领先美国\n答案：", "target": "军事", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "这是关于哪方面的新闻： 故事,文化,娱乐,体育,财经,房产,汽车,教育,科技,军事,旅游,国际,股票,农业,游戏？未来5年，教师会成为高收入人群吗？\n答案：", "target": "国际", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "阅读下面短文，从短文后给出的候选项中选出最佳选项。\n 新浪体育讯叠泉自开业以来，以其球场精良的设计、球会周到的服务，在业界的影响力不断提高，吸引了大批高尔夫爱好者慕名来到球会，这其中包括大家__的各界知名人士，政界、财经、实业、演艺界等有社会公众影响力的人物#idiom593805#。然而他们却拥有着很多共同点：他们都是社会各界的领袖精英；他们都在各自的领域颇有建树；他们都在接触叠泉后被其美丽而又富有挑战的场地所折服，#idiom593806#。 \n 候选项:神龙见首，各式各样，耳熟能详，不一而足，一应俱全，流连忘反，不胜枚举，沾沾自喜，一无所有，衣食住行。最佳选项是：", "target": "耳熟能详", "answer_choices": ["神龙见首", "各式各样", "耳熟能详", "不一而足", "一应俱全", "流连忘反", "不胜枚举", "沾沾自喜", "一无所有", "衣食住行"], "type": "mrc"}
{"input": "唐音是日本汉字音（音读）的一类。广义的「唐音」（唐宋音）指镰仓时代以后直至近代传入日本的汉字音，也就是明清时期的南方标准语「南京官话」。包含室町时代传入的「宋音」与狭义的「唐音」，即江户时代（明清）传入的汉字音。「唐音」的「唐」与「吴音」的「吴」和「汉音」的「汉」一样，并非指朝代，而是对中国的泛称。本文以论述狭义的唐音为主。江户时代传入的「唐音」与之前的「宋音」一样，主要限于佛典诵读及学问研究等，对一般用语的影响很小，仅限于特定的词语。唐音内部尚有不同的系统。就来源而言，大体分为以下三系。第一是隐元隆琦（福州府福清县人）于承应三年（1654）渡日后建立的黄檗宗所传承的用于诵读清规的明代音。第二是延宝五年（1677）渡日的曹洞宗心越派开祖心越兴俦（杭州人）所传的清规和琴谱（明乐）的诵读音。第三是江户时代的汉语学者（1674-1728）及韵镜学者文雄（1700-1763）等研究者通过长崎的通事（翻译官）等所学的中国音。有坂秀世氏将此三类分别称为黄檗唐音、心越系唐音和译官系唐音。这些音皆主要源于明末清初的南京官话音。相比于镰仓时代的宋音反映出更新的音韵变化。唐音由于母胎音的关系，带有明显的类似于现代官话和吴语发音的特色。甚至宕摄入声字也有的以エツ表示，如 阁ケツ。反映这些韵的韵腹为中母音。唐音的例词如下列举（此处一并列举可能为宋音的词）。椅子（イス） 蒲団（フトン） 行灯（アンドン） 行脚（アンギャ） 馅（アン）明（ミン） 清（シン） 普请（フシン） 白汤（パイタン） 石灰（シックイ） 馒头（マンジュウ）\n 从上面的段落中产生一个问题：", "target": "「唐音」的「唐」与「吴音」的「吴」和「汉音」的「汉」都指什么", "type": "mrc"}
{"input": "“还还没有,没有回来呢.”仅使用以上描述和你对世界所了解的,“有人还没有回来”是正确,错误,或未知？\n答案：", "target": "正确", "answer_choices": ["正确", "错误", "未知"], "type": "nli"}
{"input": "这些关键词“通用航空，导航系统，航图管理，航空器”代表了这篇论文的摘要：“为满足通用航空器对结构简单、价格低廉的导航系统的需求，提出一种机载便携式导航系统方案。系统以航路图作为背景，通过标定技术实现航图像素坐标与经纬度坐标的配准，并通过对航图的分割与四叉树管理，降低了对设备内存的需求，随着航空器位置更新，系统通过平移、旋转航图实现对航空器的导航。仿真实验结果表明，航空器在航图上定位精确，系统对于航图的平移、旋转响应准确，便携式导航系统可以满足通用航空器导航的需求，对通航飞行安全提供了一定的技术支持。”。这是正确的吗？\n选项：是的，不是\n答案：", "target": "不是", "answer_choices": ["是的", "不是"], "type": "classify"}
{"input": "根据短文内容，选出缺少的成语填在下划线处。\n 梅柏肯__。“你未经我的许可就擅自结婚，对我而言，要废除这个婚姻#idiom588293#。”他的眼睛闪着微光。“事实上，我相信你会发现登记你们结婚的记录员已经神秘失踪，而替你们主持婚礼的牧师已搬到法国。你想要证明自己结了婚恐怕是难上加难。” \n 候选成语：借花献佛，嗤之以鼻，易如反掌，投桃报李，求之不得，大失所望，虚位以待，无人之境，喜出望外，落井下石。 正确答案是：", "target": "嗤之以鼻", "answer_choices": ["借花献佛", "嗤之以鼻", "易如反掌", "投桃报李", "求之不得", "大失所望", "虚位以待", "无人之境", "喜出望外", "落井下石"], "type": "mrc"}
{"input": "这是关于哪方面的新闻？买家付了款却没有购房资格，卖家能解除房屋买卖合同吗？\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "房产", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "阅读短文：\n 方宏进在与律师商量后决定于今日将__于天下。方宏进昨日接受了个别媒体的电话采访，并不避讳自己现在很麻烦。据悉，方宏进身上牵扯的官司不止此次今麦郎这一起，之前还和多家企业发生矛盾，精通金融知识的他一直希望在商业场上大展拳脚，加之其之前央视名嘴的身份，他一直坚信自己能成功。不过，成立了北京澳卫时代广告公司(简称澳卫)的他生意方面却不顺利，记者昨日得悉，该公司已被吊销了营业执照，公司原址也已易主。记者从方宏进一位朋友那边了解到，方宏进经常用酒精麻痹自己，日前接受记者电话采访，还用一起喝酒来“打掩护”，拒绝回应实质性内容。 \n 从候选成语“扫地出门，一网打尽，顺藤摸瓜，狗血喷头，真相大白，走投无路，逍遥法外，治病救人，东窗事发，名正言顺”中选出最适合填在下划线处的成语。正确答案是：", "target": "真相大白", "answer_choices": ["扫地出门", "一网打尽", "顺藤摸瓜", "狗血喷头", "真相大白", "走投无路", "逍遥法外", "治病救人", "东窗事发", "名正言顺"], "type": "mrc"}
{"input": "“也是作践你自己,好歹我总是你的女儿”我们这样说有道理吗“我是你的女儿改变不了”？是的,不是,或也许？\n答案：", "target": "是的", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "阅读以下文章，并选择一个合适的成语。文章：\n新浪娱乐讯一向在银幕上保持文艺、内敛气质的黄璐，近日在最新写真中彰显出自身阳光、青春的一面，粉色系运动装扮搭配__的绿茵场背景，如夏日般朝气蓬勃的年轻气息扑面而来，吸引众人目光。\n 候选成语：郁郁葱葱，万家灯火，高楼大厦，车水马龙，欣欣向荣，浮光掠影，东西南北，乔装打扮，下里巴人，四通八达。答案是：", "target": "郁郁葱葱", "answer_choices": ["郁郁葱葱", "万家灯火", "高楼大厦", "车水马龙", "欣欣向荣", "浮光掠影", "东西南北", "乔装打扮", "下里巴人", "四通八达"], "type": "mrc"}
{"input": "阅读以下对话并回答问题。\n女：今天已经三月十五号了，那个调研报告什么时候可以完成？男：下个月中旬应该可以。问题：男的打算什么时候完成报告？选项：3月初,3月15号,4月中旬,4月底\n答案：", "target": "4月中旬", "answer_choices": ["3月初", "3月15号", "4月中旬", "4月底"], "type": "mrc"}
{"input": "阅读下列论文摘要，然后判断下面的这些关键词是否都是论文摘要合适的关键词？\n摘要：集成多跳中继技术的WiMAXMesh网络中,当发送功率和信道数目一定时,用户接入链路的传输速率直接取决于用户到中继的距离.在满足用户到中继距离要求的条件下,研究最少中继部署问题具有保证网络性能、降低组网成本的意义.文中将该问题转化为最少团划分问题,基于用户邻居信息提出启发式算法MAXDCP,基于用户位置信息提出启发式算法GEOCP.模拟结果表明:与该问题的最新算法MIS相比,在相同时间复杂度下,MAXDCP部署中继的个数平均减少23.8％,GEOCP平均减少35％；与已有PTAS算法HS相比,GEOCP部署中继个数平均减少18.5％,且时间复杂度更低.MAXDCP和GEOCP很好地保证了网络性能、降低了组网成本.\n关键词：问题，信息，中继，组网。答案是：\n选项：是的，不是\n答案：", "target": "不是", "answer_choices": ["是的", "不是"], "type": "classify"}
{"input": "哪个类别最好的描述了这篇新闻？芦淞区档案史志局指导档案规范化管理工作\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "财经", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "根据短文内容，选出缺少的成语填在下划线处。\n 慢慢地，“朝圣”变成对亚洲无法满足的好奇，而不是倒拨世纪之钟的时针，寻觅历史的源头。于是，他想到哪儿就到哪儿，不管亚历山大大帝是不是到过那个地方。他骑马翻过东土耳其的__，看见积雪覆盖着山坡，从撒哈拉大沙漠#idiom598242#吹来的黄沙，又将那山坡变成粉红色。现在，让他#idiom598243#的是，大自然神奇的力量和人类如何面对大自然、改造大自然。 \n 候选成语：崇山峻岭，冰天雪地，肃然起敬，一望无际，翻山越岭，各抒己见，一马平川，玄之又玄，开诚布公，成年累月。 正确答案是：", "target": "崇山峻岭", "answer_choices": ["崇山峻岭", "冰天雪地", "肃然起敬", "一望无际", "翻山越岭", "各抒己见", "一马平川", "玄之又玄", "开诚布公", "成年累月"], "type": "mrc"}
{"input": "摘要：为了解汉族民间童帽所隐含的民俗审美及民俗文化,以江南大学民间服饰传习馆藏品为研究对象,通过实物归纳法对其装饰用色、图案、配件,以及装饰元素的布局特点、装饰纹样造型特点进行分析研究.结果表明:近代汉族民间童帽装饰元素丰富,充满童趣,形成了自己的装饰规范,较其他类服饰更具特色;童帽装饰元素与民间生活密切相关,并非偶然形成.其丰富的文化内涵为研究与儿童相关的民俗风俗提供参考,为儿童服饰设计提供了丰富的素材.\n 以下的关键词都是这篇摘要合适的关键词吗？关键词：童帽，图案，装饰。答案是：\n选项：是的，不是\n答案：", "target": "不是", "answer_choices": ["是的", "不是"], "type": "classify"}
{"input": "给定“王琦瑶嘴里说抱歉的话,心里却想:严师母的意思其实是说她不识抬举”保证是真实的吗“王琦瑶在心里反思以后该怎么做的更好”？是的,不是,或也许？\n答案：", "target": "不是", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "给定“当然了,当然我这身材等于男模横着放,所以我不走秀,我坐秀”保证是真实的吗““我”喜欢坐着不爱动”？是的,不是,或也许？\n答案：", "target": "也许", "answer_choices": ["是的", "不是", "也许"], "type": "nli"}
{"input": "哪个类别最好的描述了这篇新闻？魅力乡村｜忻州岢岚宋家沟村新貌\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "旅游", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "\n段落：日本传统歌舞剧场有一条奇特的规定：观众即使看到入迷处，也只能心领神会，而不准喝彩，否则会被他人侧目而视。而台下寥寥无几的喝彩者则是剧院特邀的职业喝彩师，受过专门的喝彩训练，熟谙什么时候用什么方式喝彩，以便同台上的演员上下呼应，使演出更加趣味盎然。这些职业喝彩师多为男性，社会地位颇高，著名的喝彩大师甚至同演员齐名。他们可以自由出入剧场，坐特等包厢，有的剧团和剧院还特邀大名鼎鼎的喝彩大师光临以抬高身价。自然，喝彩大师领取的报酬也很高。不过，现在日本的喝彩师已越来越少，因而培养职业喝彩师已成为日本传统歌舞的当务之急。 \n问：目前急需解决的是什么? 选项：邀请喝彩大师，抬高喝彩大师身份，喝彩大师能自由出入，尽快培养职业喝彩师 \n答案：", "target": "尽快培养职业喝彩师", "type": "mrc", "answer_choices": ["邀请喝彩大师", "抬高喝彩大师身份", "喝彩大师能自由出入", "尽快培养职业喝彩师"]}
{"input": "摘要：针对采用一次二阶矩法计算复杂、高度非线性功能函数的可靠指标时,求解功能函数对随机变量的偏导数极其困难,并且偏导数形式非常复杂等问题,提出用响应面函数代替原功能函数的方法,使其求导过程方便,并且使偏导数形式转化为随机变量的线性表达式,便于程序化求解.然后以计算三维Hoek-Brown强度准则的可靠度为例,确认响应面法在复杂、高度非线性功能函数可靠度计算中的可行性,并与变量代换法和复合函数求导法则的计算结果进行比较,说明利用响应面法计算的结果具有较高的精度.最后,用响应面法分析强度准则参数分布类型和岩体参数之间的相关性对三维Hoek-Brown准则可靠度的影响规律.研究结果表明:该方法具有较高精度;强度准则参数分布类型对可靠指标的敏感性较弱;岩体参数的负相关系数与可靠指标线性相关,对可靠指标的影响不大.\n 以下的关键词都是这篇摘要合适的关键词吗？关键词：Hoek-Brown准则，功能，响应面法。答案是：\n选项：是的，不是\n答案：", "target": "不是", "answer_choices": ["是的", "不是"], "type": "classify"}
{"input": "以下两句话的意思相同的吗？“怎么我的蚂蚁借呗不能用了”，“怎么我不能使用蚂蚁借呗”。选项：是的，不是。答案：", "target": "是的", "answer_choices": ["是的", "不是"], "type": "classify"}
{"input": "“现在婴儿的健康状况仍很严重”记住上面的文字,考虑:“婴儿已经完全康复了。”这是总是,绝不,或有时正确的？\n答案：", "target": "绝不", "answer_choices": ["总是", "绝不", "有时"], "type": "nli"}
{"input": "这是一个成语填空任务。上文是：早上锻炼还可以提高你一天的。 \n下文是:，所以调整一下作息时间，早起30分钟，锻炼一下吧。导语：如果你2011年的计划之一是减肥，希望你在1号的时候没有满脑子想着“从明天开始”减肥没有捷径，但是可以有“jumpstart”，就是一个见效快的开始。那些“常年”减肥的女性朋友们，都应当知道减肥最难得是后期的坚持和养成一个健康的生活方式。\n候选的成语：安然无恙，误打误撞，起死回生，新陈代谢，故态复萌，自食其力，死里逃生，因祸得福，返老还童，开山祖师。请问：我们应该填写哪个成语？\n答案：", "target": "新陈代谢", "answer_choices": ["安然无恙", "误打误撞", "起死回生", "新陈代谢", "故态复萌", "自食其力", "死里逃生", "因祸得福", "返老还童", "开山祖师"], "type": "mrc"}
{"input": "阅读以下段落：\n我想找个演外国旧片的影院，走了两家都满座。走到一家剧场，有人迎上来问我要不要退票。我只肯出一张电影票的价，那人踌躇一下，索性把票子白送给我，我进剧场时不禁有些怀疑。剧场里只有稀稀拉拉儿个观众，台上一个古装少女在跳着徐缓但十分舒展的中国古典舞。水袖在淡蓝的光中拖来曳去，腰肢婀娜地扭动，筝和琵琶流水般地倾泻，天幕一片辽远清丽的冷调子。曲终舞罢，灯光暗下来。尽管我很入迷，也没鼓掌。舞台再次亮起来时，这个姑娘穿得很少地跳出来。跳了一会儿我才明白，她跳的是一个神话中的女英雄。在共工那个倒霉蛋头触不周山、造成__的严重后果后，这个女人像瓦匠一样把天重新砌好，使我们人类得以继续繁衍。据说，也是这个女人，同她的同胞交尾产卵，提供了第一批人种。值得欣慰的是编导没让这个女孩子裹上一层蛇皮，否则，她就不能向我们展现她那双极富表现力、#idiom598598#的腿。最后，我还是觉得扫兴。我以为不该让一个女孩子向成年人表现雄壮、慈悲，即使她是好心眼。我对这个女孩子印象深刻，因为她表现#idiom598599#后接踵而来的死亡很传神，简直可以说死得#idiom598600#。\n其中下划线处需要填写成语，有以下候选项：生气勃勃，洋洋得意，明媒正娶，怨气冲天，内忧外患，阒其无人，功成名遂，祸从天降，祸不单行，天塌地陷。下划线处合适的成语是：", "target": "天塌地陷", "answer_choices": ["生气勃勃", "洋洋得意", "明媒正娶", "怨气冲天", "内忧外患", "阒其无人", "功成名遂", "祸从天降", "祸不单行", "天塌地陷"], "type": "mrc"}
{"input": "这个是关于哪方面的App应用程序的描述？银行，社区，电商，支付，经营，卡牌，借贷，驾校，理财，职考，新闻，旅游，交通，魔幻，医疗，影像，动作，工具，体育，小说，运动，相机，工具，快递，教育，股票，菜谱，行车，仙侠，亲子，购物，射击，漫画，小学，同城，成人，求职，电子，艺术，赚钱，约会，经营，兼职，视频，音乐，英语，棋牌，摄影，养生，办公，政务，视频，论坛，彩票，直播，其他，休闲，策略，通讯，买车，违章，地图，民航，电台，语言，搞笑，婚恋，超市，养车，杂志，在线，家政，影视，装修，资讯，社交，餐饮，美颜，挂号，飞行，预定，票务，笔记，买房，外卖，母婴，打车，情侣，日程，租车，博客，百科，绘画，铁路，生活，租房，酒店，保险，问答，收款，竞技，唱歌，技术，减肥，工作，团购，记账，女性，公务，二手，美妆，汽车，行程，免费，教辅，两性，出国，婚庆，民宿界面简洁清晰，没有多余的装饰，方便您更加直观的查阅分析各彩种信息动态。主推时下热门彩种的开奖信息、历史开奖、走势分析、预测选号、彩种排行等。是您分析走势的必备工具。,,提升体验，修复部分问题。\n答案：", "target": "彩票", "answer_choices": ["银行", "社区", "电商", "支付", "经营", "卡牌", "借贷", "驾校", "理财", "职考", "新闻", "旅游", "交通", "魔幻", "医疗", "影像", "动作", "工具", "体育", "小说", "运动", "相机", "工具", "快递", "教育", "股票", "菜谱", "行车", "仙侠", "亲子", "购物", "射击", "漫画", "小学", "同城", "成人", "求职", "电子", "艺术", "赚钱", "约会", "经营", "兼职", "视频", "音乐", "英语", "棋牌", "摄影", "养生", "办公", "政务", "视频", "论坛", "彩票", "直播", "其他", "休闲", "策略", "通讯", "买车", "违章", "地图", "民航", "电台", "语言", "搞笑", "婚恋", "超市", "养车", "杂志", "在线", "家政", "影视", "装修", "资讯", "社交", "餐饮", "美颜", "挂号", "飞行", "预定", "票务", "笔记", "买房", "外卖", "母婴", "打车", "情侣", "日程", "租车", "博客", "百科", "绘画", "铁路", "生活", "租房", "酒店", "保险", "问答", "收款", "竞技", "唱歌", "技术", "减肥", "工作", "团购", "记账", "女性", "公务", "二手", "美妆", "汽车", "行程", "免费", "教辅", "两性", "出国", "婚庆", "民宿"], "type": "classify"}
{"input": "带着问题来阅读文章并回答问题：\n问：教授想说明什么道理? \n选项：装满杯子可以有多种方式，如何去解决生活中的问题，人生必须要实现一些目标，别让烦恼和忧郁占据生活 \n段落：一位教授在一个空杯子里装满大石块，又倒进一些小石子，并轻轻摇动杯子，让小石子滚进石块之间的空隙；然后教授拿出一些沙子倒进杯子，摇动杯子，把小石子间的空隙都填满；最后他又往杯子里倒水，把杯子所有的空间都填满。做完这些，教授对学生们说：“现在，我想让大家把这个杯子理解为生活。里面的大石块代表生命中最珍贵的东西，比如说家庭、伴侣、健康、孩子等等，所有这些对我们来说都极为重要，一旦失去将永远无法弥补；小石子代表生命中较为重要的东西，如工作、房子、车子等等；沙子代表生命中的日常小事；水代表烦恼、忧郁。请记住，如果我们先把水和沙子装进杯子，那就没有空间去装大石块和小石子了。”\n答案：", "target": "别让烦恼和忧郁占据生活", "type": "mrc", "answer_choices": ["装满杯子可以有多种方式", "如何去解决生活中的问题", "人生必须要实现一些目标", "别让烦恼和忧郁占据生活"]}
{"input": "对话：男：欢迎你，刘经理，好久不见了。女：是啊，如果不是因为工作，我们还真是难得见一次面。男：这次我要好好儿请你吃个饭，上次你走得太急了。女：那就太谢谢你了。问题：他们可能是什么关系？选项：夫妻,朋友,师生\n答案：", "target": "朋友", "answer_choices": ["夫妻", "朋友", "师生"], "type": "mrc"}
{"input": "阅读文章：\n“没关系，”他尽量__地说，“我也迟到了。杰克和米莉。布坎南打架了，我正要走的时候他来到我家。我给他吃了一杯酒，打发他上床了。”他为她倒了一杯酒，可她没有接杯子。“他就是你办公室的那位吗？我是说，在卡尔参议员办公室工作的那位吗？”她虽然没见过他的同事，但是他们的\n其中下划线的地方需要填写成语，有以下候选的成语：心平气和，以理服人，认祖归宗，开诚布公，依然故我，生吞活剥，和颜悦色，将心比心，不动声色，一本正经。正确的成语是：", "target": "心平气和", "answer_choices": ["心平气和", "以理服人", "认祖归宗", "开诚布公", "依然故我", "生吞活剥", "和颜悦色", "将心比心", "不动声色", "一本正经"], "type": "mrc"}
{"input": "这是关于哪方面的新闻？有哪些娱乐圈里面的明星追星？\n选项：故事，文化，娱乐，体育，财经，房产，汽车，教育，科技，军事，旅游，国际，股票，农业，游戏\n答案：", "target": "娱乐", "answer_choices": ["故事", "文化", "娱乐", "体育", "财经", "房产", "汽车", "教育", "科技", "军事", "旅游", "国际", "股票", "农业", "游戏"], "type": "classify"}
{"input": "摘要：提应用常规观测资料、NCEP再分析资料，对比分析了山东两次春季黄淮气旋暴雨落区异同点。发现春季影响山东的黄淮气旋暴雨区集中出现在气旋中心北侧的偏东风中，且主要位于东北气流中。暴雨区偏北的程度，与影响系统的后倾程度及我国东北地区是否存在高压有关。当系统明显后倾时，锋面坡度小，暖湿气流沿锋面向北爬升的更远，暴雨区更偏北；当我国东北地区存在高压时，其南侧东北气流经渤海侵入850hPa低涡后部，与低涡前东南气流在风向上渐近辐合，在低涡北侧产生辐合中心，从而产生暴雨区。此外，地面东北风形成的冷垫，有利于南方暖湿气流向北爬升。实际暴雨落区预报中，需综合分析系统的空间结构、周围系统的影响及温度场的配置等。 \n关键词：hPa低涡，5，暴雨落区，系统空间结构。请问：上面的关键词都是这篇摘要合适的关键词吗？\n选项：是的，不是\n答案：", "target": "是的", "answer_choices": ["是的", "不是"], "type": "classify"}
### 使用pCLUE数据集进行模型训练
* 使用pCLUE数据集在colab上进行训练、预测和效果验证, pytorch实现
[](https://colab.research.google.com/drive/1QIQDWAACkV7-iRrkrk18XrRjEekMhOtv?usp=sharing)
| 25,634 | [
[
-0.06439208984375,
-0.04803466796875,
0.0249481201171875,
0.01097869873046875,
-0.017822265625,
0.001789093017578125,
-0.003231048583984375,
-0.01454925537109375,
0.047332763671875,
0.01435089111328125,
-0.036956787109375,
-0.045318603515625,
-0.038665771484375,... |
KonradSzafer/stackoverflow_python_preprocessed | 2023-03-04T23:35:06.000Z | [
"task_categories:question-answering",
"size_categories:1K<n<10K",
"language:en",
"region:us"
] | KonradSzafer | null | null | 6 | 11 | 2023-02-25T17:32:31 | ---
dataset_info:
features:
- name: title
dtype: string
- name: answer
dtype: string
- name: question
dtype: string
splits:
- name: train
num_bytes: 5119086
num_examples: 3296
download_size: 1939470
dataset_size: 5119086
task_categories:
- question-answering
language:
- en
pretty_name: Stack Overflow Python - Preprocessed
size_categories:
- 1K<n<10K
---
# Dataset Card for "stackoverflow_python_preprocessed"
This is a preprocessed version of the [stackoverflow_python] dataset.
Questions and answers were filtered to only include questions with more than 100 votes and answers with more than 5 votes.
The dataset has been converted from HTML to plain text and only includes the title, question, and answer columns.
## Additional Information
### License
All Stack Overflow user contributions are licensed under CC-BY-SA 3.0 with attribution required.
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 1,025 | [
[
-0.052337646484375,
-0.050445556640625,
0.01611328125,
0.02203369140625,
-0.023651123046875,
0.00372314453125,
-0.0045928955078125,
-0.0138397216796875,
0.034942626953125,
0.0643310546875,
-0.0574951171875,
-0.0452880859375,
-0.0271453857421875,
0.0154037475... |
sebchw/musdb18 | 2023-03-23T08:28:41.000Z | [
"region:us"
] | sebchw | MUSDB18 music source separation dataset
to open original stem file (mp4), which is done internally you need stempeg library.
Outcome of mp4 file is a 3 dimensional np_array [n_stems, n_samples, sample_rate].
firt dimension meanings: {
0: mixture.
1: drugs,
2: bass,
3: others,
4:vocals,
}
Original dataset is not cutted in any parts, but here I cut each song in 10 seconds chunks with 1 sec overlap. | null | 0 | 11 | 2023-03-06T16:35:07 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
AnonymousSub/MedQuAD_Context_Question_Answer_Triples_TWO | 2023-03-14T18:17:38.000Z | [
"region:us"
] | AnonymousSub | null | null | 4 | 11 | 2023-03-14T18:17:35 | ---
dataset_info:
features:
- name: Contexts
dtype: string
- name: Questions
dtype: string
- name: Answers
dtype: string
splits:
- name: train
num_bytes: 190839732
num_examples: 47441
download_size: 21760499
dataset_size: 190839732
---
# Dataset Card for "MedQuAD_Context_Question_Answer_Triples_TWO"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 469 | [
[
-0.0382080078125,
-0.038421630859375,
0.02655029296875,
0.01471710205078125,
-0.01318359375,
-0.01059722900390625,
0.0241241455078125,
-0.011077880859375,
0.0433349609375,
0.04449462890625,
-0.045684814453125,
-0.036041259765625,
-0.0311126708984375,
-0.0126... |
maxcembalest/boston_housing | 2023-03-15T02:14:24.000Z | [
"region:us"
] | maxcembalest | null | null | 0 | 11 | 2023-03-15T02:13:58 | Entry not found | 15 | [
[
-0.021392822265625,
-0.01494598388671875,
0.05718994140625,
0.028839111328125,
-0.0350341796875,
0.046539306640625,
0.052490234375,
0.00507354736328125,
0.051361083984375,
0.01702880859375,
-0.052093505859375,
-0.01494598388671875,
-0.06036376953125,
0.03790... |
musabg/commoncrawl-tr | 2023-05-09T20:04:43.000Z | [
"region:us"
] | musabg | null | null | 1 | 11 | 2023-03-15T20:40:03 | ---
dataset_info:
features:
- name: id
dtype: int64
- name: text
dtype: string
- name: meta
struct:
- name: warc_headers
struct:
- name: warc-record-id
dtype: string
- name: warc-date
dtype: string
- name: content-type
dtype: string
- name: content-length
dtype: int32
- name: warc-type
dtype: string
- name: warc-identified-content-language
dtype: string
- name: warc-refers-to
dtype: string
- name: warc-target-uri
dtype: string
- name: warc-block-digest
dtype: string
- name: identification
struct:
- name: label
dtype: string
- name: prob
dtype: float32
- name: harmful_pp
dtype: float32
- name: tlsh
dtype: string
- name: quality_warnings
sequence: string
- name: categories
sequence: string
- name: sentence_identifications
list:
- name: label
dtype: string
- name: prob
dtype: float32
splits:
- name: train
num_bytes: 85952224217
num_examples: 13327165
download_size: 46952332972
dataset_size: 85952224217
---
# Dataset Card for "commoncrawl-tr"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 1,373 | [
[
-0.037506103515625,
-0.026336669921875,
0.00738525390625,
0.003925323486328125,
-0.044036865234375,
0.01561737060546875,
0.0264434814453125,
-0.022308349609375,
0.07098388671875,
0.0287628173828125,
-0.06048583984375,
-0.068359375,
-0.03802490234375,
-0.0147... |
semeru/code-code-CodeCompletion-TokenLevel-Python | 2023-03-24T14:10:30.000Z | [
"license:mit",
"region:us"
] | semeru | null | null | 0 | 11 | 2023-03-22T03:21:32 | ---
license: mit
Programminglanguage: "python"
version: "python3"
Date: "From paper [Probabilistic for Code with Decision trees](https://files.sri.inf.ethz.ch/website/papers/oopsla16-dt.pdf)(2016- paper release date)"
Contaminated: "Very Likely"
Size: "Standard Tokenizer (TreeSitter)"
---
### Dataset is imported from CodeXGLUE and pre-processed using their script.
# Where to find in Semeru:
The dataset can be found at /nfs/semeru/semeru_datasets/code_xglue/code-to-code/CodeCompletion-token/dataset/py150 in Semeru
# CodeXGLUE -- Code Completion (token level)
**Update 2021.07.30:** We update the code completion dataset with literals normalized to avoid sensitive information.
Here is the introduction and pipeline for token level code completion task.
## Task Definition
Predict next code token given context of previous tokens. Models are evaluated by token level accuracy.
Code completion is a one of the most widely used features in software development through IDEs. An effective code completion tool could improve software developers' productivity. We provide code completion evaluation tasks in two granularities -- token level and line level. Here we introduce token level code completion. Token level task is analogous to language modeling. Models should have be able to predict the next token in arbitary types.
## Dataset
The dataset is in python.
### Dependency
- python 3.7
### Github Java Corpus
We use java corpus dataset mined by Allamanis and Sutton, in their MSR 2013 paper [Mining Source Code Repositories at Massive Scale using Language Modeling](https://homepages.inf.ed.ac.uk/csutton/publications/msr2013.pdf). We follow the same split and preprocessing in Karampatsis's ICSE 2020 paper [Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code](http://homepages.inf.ed.ac.uk/s1467463/documents/icse20-main-1325.pdf).
### Data Format
Code corpus are saved in txt format files. one line is a tokenized code snippets:
```
<s> from __future__ import unicode_literals <EOL> from django . db import models , migrations <EOL> class Migration ( migrations . Migration ) : <EOL> dependencies = [ <EOL> ] <EOL> operations = [ <EOL> migrations . CreateModel ( <EOL> name = '<STR_LIT>' , <EOL> fields = [ <EOL> ( '<STR_LIT:id>' , models . AutoField ( verbose_name = '<STR_LIT>' , serialize = False , auto_created = True , primary_key = True ) ) , <EOL> ( '<STR_LIT:name>' , models . CharField ( help_text = b'<STR_LIT>' , max_length = <NUM_LIT> ) ) , <EOL> ( '<STR_LIT:image>' , models . ImageField ( help_text = b'<STR_LIT>' , null = True , upload_to = b'<STR_LIT>' , blank = True ) ) , <EOL> ] , <EOL> options = { <EOL> '<STR_LIT>' : ( '<STR_LIT:name>' , ) , <EOL> '<STR_LIT>' : '<STR_LIT>' , <EOL> } , <EOL> bases = ( models . Model , ) , <EOL> ) , <EOL> ] </s>
```
### Data Statistics
Data statistics of py150 dataset are shown in the below table, note that there doesn't exist dev set in the origin py150 dataset, we select 5,000 files in the original train set as dev set.
| Data Split | #Files | #Tokens |
| ----------- | :---------: | :---------: |
| Train | 95,000 | 72.1M |
| Dev | 5,000 | 4.4M |
| Test | 50,000 | 37.3M |
| 3,258 | [
[
-0.040008544921875,
-0.016143798828125,
0.00592803955078125,
0.016265869140625,
-0.012237548828125,
-0.007328033447265625,
-0.01494598388671875,
-0.0278472900390625,
0.00925445556640625,
0.047149658203125,
-0.0341796875,
-0.058624267578125,
-0.03448486328125,
... |
pythainlp/thaigov-v2-corpus-22032023 | 2023-03-22T08:44:49.000Z | [
"size_categories:10K<n<100K",
"language:th",
"license:cc0-1.0",
"region:us"
] | pythainlp | null | null | 2 | 11 | 2023-03-22T07:57:03 | ---
dataset_info:
features:
- name: title
dtype: string
- name: context
dtype: string
- name: url
dtype: string
splits:
- name: train
num_bytes: 252319219
num_examples: 30380
download_size: 85313027
dataset_size: 252319219
license: cc0-1.0
language:
- th
size_categories:
- 10K<n<100K
---
# Dataset Card for "thaigov-v2-corpus-22032023"
This corpus made from Thaigov v2 corpus in 22 Mar 2023. [https://github.com/PyThaiNLP/thaigov-v2-corpus/releases/tag/22032023](https://github.com/PyThaiNLP/thaigov-v2-corpus/releases/tag/22032023)
Corups: [https://github.com/PyThaiNLP/thaigov-v2-corpus](https://github.com/PyThaiNLP/thaigov-v2-corpus)
## English
- Data from Thai government website. https://www.thaigov.go.th
- This part of PyThaiNLP Project.
- Compiled by Mr.Wannaphong Phatthiyaphaibun
- License Dataset is public domain.
## Data format
- 1 file, 1 news, which is extracted from 1 url.
```
topic
(Blank line)
content
content
content
content
content
(Blank line)
ที่มา (URL source) : http://www.thaigov.go.th/news/contents/details/NNN
```
## Thai
- เป็นข้อมูลที่รวบรวมข่าวสารจากเว็บไซต์รัฐบาลไทย https://www.thaigov.go.th
- โครงการนี้เป็นส่วนหนึ่งในแผนพัฒนา [PyThaiNLP](https://github.com/PyThaiNLP/)
- รวบรวมโดย นาย วรรณพงษ์ ภัททิยไพบูลย์
- ข้อมูลที่รวบรวมในคลังข้อความนี้เป็นสาธารณสมบัติ (public domain) ตามพ.ร.บ.ลิขสิทธิ์ พ.ศ. 2537 มาตรา 7 (สิ่งต่อไปนี้ไม่ถือว่าเป็นงานอันมีลิขสิทธิ์ตามพระราชบัญญัตินี้ (1) ข่าวประจำวัน และข้อเท็จจริงต่างๆ ที่มีลักษณะเป็นเพียงข่าวสารอันมิใช่งานในแผนกวรรณคดี แผนกวิทยาศาสตร์ หรือแผนกศิลปะ [...] (3) ระเบียบ ข้อบังคับ ประกาศ คำสั่ง คำชี้แจง และหนังสือตอบโต้ของกระทรวง ทบวง กรม หรือหน่วยงานอื่นใดของรัฐหรือของท้องถิ่น [...])
**สามารถติดตามประวัติการแก้ไขคลังข้อความนี้ได้ผ่านระบบ Git**
### จำนวนข่าว
- วันเริ่มต้นโครงการ 17 ก.ย. 2563
### รูปแบบข้อมูล
- 1 ไฟล์ 1 ข่าว ซึ่งดึงมาจาก 1 url
```
หัวเรื่อง
(บรรทัดว่าง)
เนื้อความ
เนื้อความ
เนื้อความ
เนื้อความ
เนื้อความ
(บรรทัดว่าง)
ที่มา : http://www.thaigov.go.th/news/contents/details/NNN
```
### รายละเอียดชื่อไฟล์
- ชื่อหมวดหมู่_จำนวนที่ของข่าว.txt
### Script
- run.py สำหรับเก็บข้อมูลจากหน้าเว็บ โดยจะดึงหน้าเว็บจาก url ```http://www.thaigov.go.th/news/contents/details/NNN``` โดยที่ NNN คือเลขจำนวนเต็ม
- เปลี่ยนค่าตัวแปร i ในไฟล์เป็นเลขที่ต้องการเริ่มเก็บ
- clean.py สำหรับทำความสะอาดข้อมูลเบื้องต้น โดยจะลบช่องว่างหน้าและท้ายบรรทัด ลบบรรทัดว่าง
- ```clean.py ชื่อไฟล์```
- ```clean.py ชื่อไฟล์1 ชื่อไฟล์2```
- ```clean.py *.txt```
We build Thai NLP.
PyThaiNLP | 2,524 | [
[
-0.020233154296875,
-0.03887939453125,
0.0047149658203125,
0.021636962890625,
-0.037445068359375,
-0.00710296630859375,
-0.0266571044921875,
-0.007755279541015625,
0.0357666015625,
0.037445068359375,
-0.0172882080078125,
-0.03167724609375,
-0.036102294921875,
... |
MortenTabaka/LandCover-Aerial-Imagery-for-semantic-segmentation | 2023-03-26T17:28:43.000Z | [
"task_categories:image-segmentation",
"license:cc-by-nc-sa-4.0",
"arxiv:2005.02264",
"region:us"
] | MortenTabaka | null | null | 4 | 11 | 2023-03-26T14:36:08 | ---
license: cc-by-nc-sa-4.0
task_categories:
- image-segmentation
---
# LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery
My project based on the dataset, can be found on Github: https://github.com/MortenTabaka/Semantic-segmentation-of-LandCover.ai-dataset
The dataset used in this project is the [Landcover.ai Dataset](https://landcover.ai.linuxpolska.com/),
which was originally published with [LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery paper](https://arxiv.org/abs/2005.02264)
also accessible on [PapersWithCode](https://paperswithcode.com/paper/landcover-ai-dataset-for-automatic-mapping-of).
**Please note that I am not the author or owner of this dataset, and I am using it under the terms of the license specified by the original author.
All credits for the dataset go to the original author and contributors.**
---
license: cc-by-nc-sa-4.0
--- | 976 | [
[
-0.032989501953125,
-0.03851318359375,
0.036529541015625,
0.0020542144775390625,
-0.028778076171875,
-0.002155303955078125,
-0.0023555755615234375,
-0.029022216796875,
0.007762908935546875,
0.04827880859375,
-0.0164947509765625,
-0.078857421875,
-0.0409851074218... |
mstz/toxicity | 2023-04-16T18:03:37.000Z | [
"task_categories:tabular-classification",
"size_categories:n<1K",
"language:en",
"license:cc",
"toxicity",
"tabular_classification",
"binary_classification",
"multiclass_classification",
"UCI",
"region:us"
] | mstz | null | null | 0 | 11 | 2023-03-31T14:59:54 | ---
language:
- en
tags:
- toxicity
- tabular_classification
- binary_classification
- multiclass_classification
- UCI
pretty_name: Toxicity
size_categories:
- n<1K
task_categories:
- tabular-classification
configs:
- encoding
- income
- income-no race
- race
license: cc
---
# Adult
The [Toxicity dataset](https://archive-beta.ics.uci.edu/dataset/728/toxicity) from the [UCI ML repository](https://archive.ics.uci.edu/ml/datasets).
The dataset includes 171 molecules designed for functional domains of a core clock protein, CRY1, responsible for generating circadian rhythm.
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-------------------|---------------------------|-----------------------------------------------------------------|
| toxicity | Binary classification | Is the molecule toxic? |
# Usage
```python
from datasets import load_dataset
dataset = load_dataset("mstz/toxicity")["train"]
``` | 1,059 | [
[
0.01067352294921875,
-0.016510009765625,
0.0144805908203125,
0.0196990966796875,
-0.032135009765625,
-0.0193023681640625,
-0.002422332763671875,
-0.0285186767578125,
0.0007719993591308594,
0.0280303955078125,
-0.059967041015625,
-0.05035400390625,
-0.03109741210... |
afmck/peanuts-flan-t5-xl | 2023-04-05T14:09:59.000Z | [
"task_categories:text-to-image",
"size_categories:10K<n<100K",
"language:en",
"license:apache-2.0",
"region:us"
] | afmck | null | null | 4 | 11 | 2023-04-05T13:16:59 | ---
license: apache-2.0
task_categories:
- text-to-image
language:
- en
pretty_name: Peanuts Dataset (Snoopy and Co.)
size_categories:
- 10K<n<100K
dataset_info:
features:
- name: image
dtype: image
- name: panel_name
dtype: string
- name: characters
sequence: string
- name: themes
sequence: string
- name: color
dtype: string
- name: year
dtype: int64
- name: caption
dtype: string
splits:
- name: train
num_bytes: 2947874869.848
num_examples: 77456
download_size: 0
dataset_size: 2947874869.848
---
# Peanut Comic Strip Dataset (Snoopy & Co.)
This is a dataset Peanuts comic strips from `1950/10/02` to `2000/02/13`.
There are `77,456` panels extracted from `17,816` comic strips.
The dataset size is approximately `4.4G`.
Each row in the dataset contains the following fields:
- `image`: `PIL.Image` containing the extracted panel.
- `panel_name`: unique identifier for the row.
- `characters`: `tuple[str, ...]` of characters included in the comic strip the panel is part of.
- `themes`: `tuple[str, ...]` of theme in the comic strip the panel is part of.
- `color`: `str` indicating whether the panel is grayscale or in color.
- `caption`: [BLIP-2_FLAN-T5-XL](https://huggingface.co/docs/transformers/main/model_doc/blip-2) generated caption from the panel.
- `year`: `int` storing the year the specific panel was released.
> **FLAN-T5-XL has a commercial use license and so this dataset can be used for commercial projects. Alternatively use [this similar dataset](https://huggingface.co/datasets/afmck/peanuts-opt-6.7b) that uses OPT-6.7B as the caption pipeline's text model, however it does not permit commercial use.**
Character and theme information was extracted from [Peanuts Wiki (Fandom)](https://peanuts.fandom.com/wiki/Peanuts_Wiki) using [Beautiful Soup](https://www.crummy.com/software/BeautifulSoup/bs4/doc/).
Images were extracted from [Peanuts Search](https://peanuts-search.com/).
Only strips with the following characters were extracted:
```
- "Charlie Brown"
- "Sally Brown"
- "Joe Cool" # Snoopy alter-ego
- "Franklin"
- "Violet Gray"
- "Eudora"
- "Frieda"
- "Marcie"
- "Peppermint Patty"
- "Patty"
- "Pig-Pen"
- "Linus van Pelt"
- "Lucy van Pelt"
- "Rerun van Pelt"
- "Schroeder"
- "Snoopy"
- "Shermy"
- "Spike"
- "Woodstock"
- "the World War I Flying Ace" # Snoopy alter-ego
```
### Extraction Details
Panel detection and extraction was done using the following codeblock:
```python
def check_contour(cnt):
area = cv2.contourArea(cnt)
if area < 600:
return False
_, _, w, h = cv2.boundingRect(cnt)
if w / h < 1 / 2: return False
if w / h > 2 / 1: return False
return True
def get_panels_from_image(path):
panels = []
original_img = cv2.imread(path)
gray = cv2.cvtColor(original_img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
invert = 255 - opening
cnts, _ = cv2.findContours(invert, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
idx = 0
for cnt in cnts:
if not check_contour(cnt): continue
idx += 1
x,y,w,h = cv2.boundingRect(cnt)
roi = original_img[y:y+h,x:x+w]
panels.append(roi)
return panels
```
`check_contour` will reject panels with `area < 600` or with aspect ratios larger than `2` or smaller than `0.5`.
Grayscale detection was done using the following codeblock:
```python
def is_grayscale(panel):
LAB_THRESHOLD = 10.
img = cv2.cvtColor(panel, cv2.COLOR_RGB2LAB)
_, ea, eb = cv2.split(img)
de = abs(ea - eb)
mean_e = np.mean(de)
return mean_e < LAB_THRESHOLD
```
Captioning was done using the standard BLIP-2 pipeline shown in the [Huggingface docs](https://huggingface.co/docs/transformers/main/model_doc/blip-2) using beam search over 10 beams and a repetition penalty of `2.0`.
Raw captions are extracted and no postprocessing is applied. You may wish to normalise captions (such as replacing "cartoon" with "peanuts cartoon") or incorporate extra metadata into prompts. | 4,296 | [
[
-0.05377197265625,
-0.042877197265625,
0.01305389404296875,
0.038330078125,
-0.017120361328125,
0.0081329345703125,
-0.002170562744140625,
-0.0360107421875,
0.037261962890625,
0.055267333984375,
-0.04510498046875,
-0.0282440185546875,
-0.037841796875,
0.0233... |
kowndinya23/Kvasir-SEG | 2023-04-05T18:47:27.000Z | [
"region:us"
] | kowndinya23 | null | null | 0 | 11 | 2023-04-05T18:47:22 | ---
dataset_info:
features:
- name: name
dtype: string
- name: image
dtype: image
- name: annotation
dtype: image
splits:
- name: train
num_bytes: 36829616.0
num_examples: 880
- name: validation
num_bytes: 8018441.0
num_examples: 120
download_size: 44672597
dataset_size: 44848057.0
---
# Dataset Card for "Kvasir-SEG"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 497 | [
[
-0.041229248046875,
-0.022003173828125,
0.01160430908203125,
0.0187835693359375,
-0.02978515625,
-0.004856109619140625,
0.016693115234375,
-0.00002682209014892578,
0.058441162109375,
0.040130615234375,
-0.056243896484375,
-0.0675048828125,
-0.043212890625,
-... |
mstz/spambase | 2023-04-16T18:02:22.000Z | [
"task_categories:tabular-classification",
"size_categories:1K<n<10K",
"language:en",
"license:cc",
"spambase",
"tabular_classification",
"binary_classification",
"UCI",
"region:us"
] | mstz | null | @misc{misc_spambase_94,
author = {Hopkins,Mark, Reeber,Erik, Forman,George & Suermondt,Jaap},
title = {{Spambase}},
year = {1999},
howpublished = {UCI Machine Learning Repository},
note = {{DOI}: \\url{10.24432/C53G6X}}
} | 0 | 11 | 2023-04-07T07:37:26 | ---
language:
- en
tags:
- spambase
- tabular_classification
- binary_classification
- UCI
pretty_name: Spambase
size_categories:
- 1K<n<10K
task_categories:
- tabular-classification
configs:
- spambase
license: cc
---
# Spambase
The [Spambase dataset](https://archive.ics.uci.edu/ml/datasets/Spambase) from the [UCI ML repository](https://archive.ics.uci.edu/ml/datasets).
Is the given mail spam?
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-------------------|---------------------------|------------------|
| spambase | Binary classification | Is the mail spam?|
# Usage
```python
from datasets import load_dataset
dataset = load_dataset("mstz/spambase")["train"]
``` | 740 | [
[
-0.031829833984375,
-0.04022216796875,
-0.0214996337890625,
0.0277862548828125,
-0.007305145263671875,
-0.023345947265625,
0.002956390380859375,
0.00916290283203125,
0.01763916015625,
0.068115234375,
-0.046295166015625,
-0.046783447265625,
-0.07855224609375,
... |
mstz/seeds | 2023-04-16T17:58:19.000Z | [
"task_categories:tabular-classification",
"size_categories:1K<n<10K",
"language:en",
"license:cc",
"seeds",
"tabular_classification",
"binary_classification",
"multiclass_classification",
"UCI",
"region:us"
] | mstz | null | @misc{misc_seeds_236,
author = {Charytanowicz,Magorzata, Niewczas,Jerzy, Kulczycki,Piotr, Kowalski,Piotr & Lukasik,Szymon},
title = {{seeds}},
year = {2012},
howpublished = {UCI Machine Learning Repository},
note = {{DOI}: \\url{10.24432/C5H30K}}
} | 0 | 11 | 2023-04-13T10:55:57 | ---
language:
- en
tags:
- seeds
- tabular_classification
- binary_classification
- multiclass_classification
- UCI
pretty_name: Page Blocks
size_categories:
- 1K<n<10K
task_categories:
- tabular-classification
configs:
- seeds
- seeds_binary
license: cc
---
# Post Operative
The [Seeds dataset](https://archive-beta.ics.uci.edu/dataset/236/seeds) from the [UCI repository](https://archive-beta.ics.uci.edu/).
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-----------------------|---------------------------|-------------------------|
| seeds | Multiclass classification.| |
| seeds_0 | Binary classification. | Is the seed of class 0? |
| seeds_1 | Binary classification. | Is the seed of class 1? |
| seeds_2 | Binary classification. | Is the seed of class 2? | | 917 | [
[
-0.0310516357421875,
-0.004947662353515625,
0.0172271728515625,
0.031524658203125,
-0.0027141571044921875,
-0.00965118408203125,
-0.002044677734375,
-0.0163726806640625,
0.0172271728515625,
0.024017333984375,
-0.040863037109375,
-0.047149658203125,
-0.0667724609... |
ktgiahieu/maccrobat2018_2020 | 2023-05-21T10:39:53.000Z | [
"license:cc-by-4.0",
"region:us"
] | ktgiahieu | null | null | 1 | 11 | 2023-04-15T21:27:11 | ---
license: cc-by-4.0
---
Modified dataset from:
Caufield, J. Harry (2019): MACCROBAT. figshare. Dataset. https://doi.org/10.6084/m9.figshare.9764942.v2
Example training notebook: https://colab.research.google.com/drive/1OzCY782KJSF0FBDS0d1CoMhfp3-RtJMV?usp=sharing
Labels:
```
0: B-Activity
1: B-Administration
2: B-Age
3: B-Area
4: B-Biological_attribute
5: B-Biological_structure
6: B-Clinical_event
7: B-Color
8: B-Coreference
9: B-Date
10: B-Detailed_description
11: B-Diagnostic_procedure
12: B-Disease_disorder
13: B-Distance
14: B-Dosage
15: B-Duration
16: B-Family_history
17: B-Frequency
18: B-Height
19: B-History
20: B-Lab_value
21: B-Mass
22: B-Medication
23: B-Nonbiological_location
24: B-Occupation
25: B-Other_entity
26: B-Other_event
27: B-Outcome
28: B-Personal_background
29: B-Qualitative_concept
30: B-Quantitative_concept
31: B-Severity
32: B-Sex
33: B-Shape
34: B-Sign_symptom
35: B-Subject
36: B-Texture
37: B-Therapeutic_procedure
38: B-Time
39: B-Volume
40: B-Weight
41: I-Activity
42: I-Administration
43: I-Age
44: I-Area
45: I-Biological_attribute
46: I-Biological_structure
47: I-Clinical_event
48: I-Color
49: I-Coreference
50: I-Date
51: I-Detailed_description
52: I-Diagnostic_procedure
53: I-Disease_disorder
54: I-Distance
55: I-Dosage
56: I-Duration
57: I-Family_history
58: I-Frequency
59: I-Height
60: I-History
61: I-Lab_value
62: I-Mass
63: I-Medication
64: I-Nonbiological_location
65: I-Occupation
66: I-Other_entity
67: I-Other_event
68: I-Outcome
69: I-Personal_background
70: I-Qualitative_concept
71: I-Quantitative_concept
72: I-Severity
73: I-Shape
74: I-Sign_symptom
75: I-Subject
76: I-Texture
77: I-Therapeutic_procedure
78: I-Time
79: I-Volume
80: I-Weight
81: O
``` | 1,722 | [
[
-0.007564544677734375,
-0.0305328369140625,
0.0270843505859375,
0.0166778564453125,
0.0015430450439453125,
-0.01380157470703125,
0.0109100341796875,
-0.0180206298828125,
0.046661376953125,
0.0325927734375,
-0.038482666015625,
-0.06475830078125,
-0.05947875976562... |
mstz/kddcup | 2023-04-17T14:29:30.000Z | [
"task_categories:tabular-classification",
"language:en",
"kddcup",
"tabular_classification",
"binary_classification",
"region:us"
] | mstz | null | null | 1 | 11 | 2023-04-17T14:22:06 | ---
language:
- en
tags:
- kddcup
- tabular_classification
- binary_classification
pretty_name: Kddcup
task_categories: # Full list at https://github.com/huggingface/hub-docs/blob/main/js/src/lib/interfaces/Types.ts
- tabular-classification
configs:
- kddcup
---
# Kddcup
The Kddcup dataset.
# Configurations and tasks
| **Configuration** | **Task** |
|-----------------------|---------------------------|
| kddcup | Multiclass classification.|
| 483 | [
[
-0.03961181640625,
-0.005687713623046875,
0.0106048583984375,
0.01514434814453125,
0.00366973876953125,
0.0233306884765625,
0.003841400146484375,
0.002513885498046875,
-0.00572967529296875,
0.0110626220703125,
-0.042083740234375,
-0.038116455078125,
-0.052612304... |
fnlp/moss-002-sft-data | 2023-04-20T16:17:16.000Z | [
"task_categories:conversational",
"task_categories:text-generation",
"size_categories:1M<n<10M",
"language:en",
"language:zh",
"license:cc-by-4.0",
"arxiv:2212.10560",
"region:us"
] | fnlp | null | null | 83 | 11 | 2023-04-20T10:14:09 | ---
license: cc-by-4.0
task_categories:
- conversational
- text-generation
language:
- en
- zh
size_categories:
- 1M<n<10M
---
# Dataset Card for "moss-002-sft-data"
## Dataset Description
- **Homepage:** [https://txsun1997.github.io/blogs/moss.html](https://txsun1997.github.io/blogs/moss.html)
- **Repository:** [https://github.com/OpenLMLab/MOSS](https://github.com/OpenLMLab/MOSS)
- **Total amount of disk used:** 2.16 GB
### Dataset Summary
An open-source conversational dataset that was used to train MOSS-002. The user prompts are extended based on a small set of human-written seed prompts in a way similar to [Self-Instruct](https://arxiv.org/abs/2212.10560). The AI responses are generated using `text-davinci-003`. The user prompts of `en_harmlessness` are from [Anthropic red teaming data](https://github.com/anthropics/hh-rlhf/tree/master/red-team-attempts).
### Data Splits
| name | \# samples |
|----------------------|-----------:|
| en_helpfulness.json | 419049 |
| en_honesty.json | 112580 |
| en_harmlessness.json | 38873 |
| zh_helpfulness.json | 447750 |
| zh_honesty.json | 142885 |
| 1,162 | [
[
-0.0297698974609375,
-0.033905029296875,
0.01496124267578125,
0.022796630859375,
-0.01377105712890625,
-0.0001392364501953125,
0.0019073486328125,
-0.0172882080078125,
0.01202392578125,
0.018524169921875,
-0.0760498046875,
-0.03704833984375,
-0.0145111083984375,... |
9wimu9/sinhala_sentences_raw | 2023-05-04T17:44:33.000Z | [
"region:us"
] | 9wimu9 | null | null | 1 | 11 | 2023-05-04T17:42:46 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
mvasiliniuc/iva-swift-codeint-clean | 2023-06-15T14:48:16.000Z | [
"task_categories:text-generation",
"task_ids:language-modeling",
"annotations_creators:crowdsourced",
"language_creators:crowdsourced",
"size_categories:100K<n<1M",
"language:code",
"license:other",
"code, swift, native iOS development, curated",
"region:us"
] | mvasiliniuc | null | null | 3 | 11 | 2023-05-09T20:20:44 | ---
annotations_creators:
- crowdsourced
license: other
language_creators:
- crowdsourced
language:
- code
task_categories:
- text-generation
tags:
- code, swift, native iOS development, curated
size_categories:
- 100K<n<1M
source_datasets: []
pretty_name: iva-swift-codeint-clean
task_ids:
- language-modeling
---
# IVA Swift GitHub Code Dataset
## Dataset Description
This is the curated IVA Swift dataset extracted from GitHub.
It contains curated Swift files gathered with the purpose to train a code generation model.
The dataset consists of 383380 swift code files from GitHub totaling ~542MB of data.
The [uncurated](https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint) dataset was created from the public GitHub dataset on Google BiqQuery.
### How to use it
To download the full dataset:
```python
from datasets import load_dataset
dataset = load_dataset('mvasiliniuc/iva-swift-codeint-clean', split='train')
```
```python
from datasets import load_dataset
dataset = load_dataset('mvasiliniuc/iva-swift-codeint-clean', split='train')
print(dataset[723])
#OUTPUT:
{
"repo_name":"jdkelley/Udacity-OnTheMap-ExampleApps",
"path":"TheMovieManager-v2/TheMovieManager/BorderedButton.swift",
"copies":"2",
"size":"2649",
"content":"...let phoneBorderedButtonExtraPadding: CGFloat = 14.0\n \n var backingColor: UIColor? = nil\n var highlightedBackingColor: UIColor? = nil\n \n // MARK: Initialization\n}",
"license":"mit",
"hash":"db1587fd117e9a835f58cf8203d8bf05",
"line_mean":29.1136363636,
"line_max":87,
"alpha_frac":0.6700641752,
"ratio":5.298,
"autogenerated":false,
"config_or_test":false,
"has_no_keywords":false,
"has_few_assignments":false
}
```
## Data Structure
### Data Fields
|Field|Type|Description|
|---|---|---|
|repo_name|string|name of the GitHub repository|
|path|string|path of the file in GitHub repository|
|copies|string|number of occurrences in dataset|
|content|string|content of source file|
|size|string|size of the source file in bytes|
|license|string|license of GitHub repository|
|hash|string|Hash of content field.|
|line_mean|number|Mean line length of the content.
|line_max|number|Max line length of the content.
|alpha_frac|number|Fraction between mean and max line length of content.
|ratio|number|Character/token ratio of the file with tokenizer.
|autogenerated|boolean|True if the content is autogenerated by looking for keywords in the first few lines of the file.
|config_or_test|boolean|True if the content is a configuration file or a unit test.
|has_no_keywords|boolean|True if a file has none of the keywords for Swift Programming Language.
|has_few_assignments|boolean|True if file uses symbol '=' less than `minimum` times.
### Instance
```json
{
"repo_name":"...",
"path":".../BorderedButton.swift",
"copies":"2",
"size":"2649",
"content":"...",
"license":"mit",
"hash":"db1587fd117e9a835f58cf8203d8bf05",
"line_mean":29.1136363636,
"line_max":87,
"alpha_frac":0.6700641752,
"ratio":5.298,
"autogenerated":false,
"config_or_test":false,
"has_no_keywords":false,
"has_few_assignments":false
}
```
## Languages
The dataset contains only Swift files.
```json
{
"Swift": [".swift"]
}
```
## Licenses
Each entry in the dataset contains the associated license. The following is a list of licenses involved and their occurrences.
```json
{
"agpl-3.0":1695,
"apache-2.0":85514,
"artistic-2.0":207,
"bsd-2-clause":3132,
"bsd-3-clause":6600,
"cc0-1.0":1409,
"epl-1.0":605,
"gpl-2.0":9374,
"gpl-3.0":18920,
"isc":808,
"lgpl-2.1":1122,
"lgpl-3.0":3103,
"mit":240929,
"mpl-2.0":8181,
"unlicense":1781
}
```
## Dataset Statistics
```json
{
"Total size": "~542 MB",
"Number of files": 383380,
"Number of files under 500 bytes": 3680,
"Average file size in bytes": 5942,
}
```
## Curation Process
* Removal of duplication files based on file hash.
* Removal of file templates. File containing the following: `___FILENAME___, ___PACKAGENAME___, ___FILEBASENAME___, ___FILEHEADER___, ___VARIABLE`
* Removal of the files containing the following words in the first 10 lines: `generated, auto-generated", "autogenerated", "automatically generated`
* Removal of the files containing the following words in the first 10 lines with a probability of 0.7: `test", "unit test", "config", "XCTest", "JUnit`
* Removal of file with the rate of alphanumeric characters below 0.3 of the file.
* Removal of near duplication based MinHash and Jaccard similarity.
* Removal of files with mean line length above 100.
* Removal of files without mention of keywords with a probability of 0.7: `struct ", "class ", "for ", "while ", "enum ", "func ", "typealias ", "var ", "let ", "protocol ", "public ", "private ", "internal ", "import "`
* Removal of files that use the assignment operator `=` less than 3 times.
* Removal of files with the ratio between the number of characters and number of tokens after tokenization lower than 1.5.
Curation process is a derivation of the one used in CodeParrot project: https://huggingface.co/codeparrot
## Data Splits
The dataset only contains a train split which is separated into train and valid which can be found here:
* Clean Version Train: https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint-clean-train
* Clean Version Valid: https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint-clean-valid
# Considerations for Using the Data
The dataset comprises source code from various repositories, potentially containing harmful or biased code,
along with sensitive information such as passwords or usernames.
| 5,691 | [
[
-0.03948974609375,
-0.0292510986328125,
0.005199432373046875,
0.009124755859375,
-0.0188751220703125,
0.0202178955078125,
-0.004199981689453125,
-0.008026123046875,
0.036895751953125,
0.0540771484375,
-0.03759765625,
-0.053253173828125,
-0.0282440185546875,
... |
rcp-meetings/rudialogsum_v2 | 2023-05-12T14:35:48.000Z | [
"task_categories:text2text-generation",
"task_categories:summarization",
"size_categories:10K<n<100K",
"language:ru",
"license:mit",
"region:us"
] | rcp-meetings | null | null | 0 | 11 | 2023-05-12T14:30:27 | ---
license: mit
task_categories:
- text2text-generation
- summarization
language:
- ru
size_categories:
- 10K<n<100K
---
Датасет dialogsum переведенный на русский язык. Глюки перевода устранены автоматической чисткой | 217 | [
[
0.004444122314453125,
-0.05133056640625,
0.035797119140625,
-0.0049285888671875,
-0.02239990234375,
-0.0015382766723632812,
0.025482177734375,
-0.004032135009765625,
0.0447998046875,
0.036956787109375,
-0.0650634765625,
-0.043975830078125,
-0.0200653076171875,
... |
scaredmeow/shopee-reviews-tl-stars | 2023-05-15T07:40:20.000Z | [
"task_categories:text-classification",
"size_categories:1K<n<10K",
"language:tl",
"license:mpl-2.0",
"reviews",
"shopee",
"doi:10.57967/hf/0656",
"region:us"
] | scaredmeow | null | null | 0 | 11 | 2023-05-13T21:13:28 | ---
license: mpl-2.0
task_categories:
- text-classification
language:
- tl
size_categories:
- 1K<n<10K
dataset_info:
features:
- name: label
dtype:
class_label:
names:
'0': 1 star
'1': 2 star
'2': 3 stars
'3': 4 stars
'4': 5 stars
- name: text
dtype: string
tags:
- reviews
- shopee
---
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:** [Enhancement to Low Resource Text Classification via Sequential Transfer Learning](#)
- **Leaderboard:**
- **Point of Contact:** [Neil Riego](mailto:neilchristianriego3@gmail.com)
### Dataset Summary
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Tagalog (TL)
## Dataset Structure
### Data Instances
A typical data point, comprises of a text and the corresponding label.
An example from the YelpReviewFull test set looks as follows:
```
{
'label': 2,
'text': 'Madaling masira yung sa may sinisintasan nya. Wala rin syang box. Sana mas ginawa pa na matibay para sana sulit yung pagkakabili'
}
```
### Data Fields
- 'text': The review texts are escaped using double quotes ("), and any internal double quote is escaped by 2 double quotes ("").
- 'label': Corresponds to the score associated with the review (between 1 and 5).
### Data Splits
The Shopee reviews tl 15 dataset is constructed by randomly taking 2100 training samples and 450 samples for testing and validation for each review star from 1 to 5.
In total there are 10500 trainig samples and 2250 each in validation and testing samples.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed] | 2,714 | [
[
-0.022857666015625,
-0.03192138671875,
-0.0036220550537109375,
0.022064208984375,
-0.025634765625,
-0.002178192138671875,
-0.0191497802734375,
-0.03631591796875,
0.0267333984375,
0.044464111328125,
-0.04833984375,
-0.058990478515625,
-0.051605224609375,
0.01... |
yankihue/turkish-news-categories | 2023-05-24T15:20:05.000Z | [
"region:us"
] | yankihue | null | null | 0 | 11 | 2023-05-24T15:19:46 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
zirui3/zhihu_qa_oa_instructions | 2023-05-25T02:49:33.000Z | [
"license:cc-by-4.0",
"region:us"
] | zirui3 | null | null | 2 | 11 | 2023-05-25T01:24:38 | ---
license: cc-by-4.0
---
# data summary
`zhihu_qa` instruction data follow `Open-Assistant`'s format
* 3k questions and 23w answsers on zhihu.com
* Questions taken from 10 popular topics:
* “Culture” (文化)
* “Education” (教育)
* “Art” (艺术)
* “University” (大学)
* “The Internet” (互联网)
* “Psychology” (心理)
* “Technology” (科技)
* “Health” (健康)
* “Career Development” (职业发展)
* “Lifestyle” (生活方式)
## sample
```json
{
"INSTRUCTION": "上海有哪些夜生活？ 老歌里面有唱到“夜上海”，那么现在的上海到底有哪些丰富的夜生活呢？",
"RESPONSE": "地点：闵行区男子技术学院（也叫MIT）去年夏季学期的一天晚上，心情不好，和同学在校园逛到凌晨一点多。去各个地方买饮料喝，在冰火吃烧烤。郊区自然不像市区这么热闹，但是这么晚了居然还有人。",
"SOURCE": "zhihu",
"meta": {
"question_id": 29639528,
"answer": 62379612,
"answer_type": "short_answers",
"tags": [
"上海",
"城市生活",
"城市",
"生活方式",
"夜生活"
]
}
}
```
| 825 | [
[
-0.03912353515625,
-0.0660400390625,
0.035888671875,
-0.0014553070068359375,
-0.0254974365234375,
-0.031463623046875,
-0.01458740234375,
-0.033782958984375,
0.0289154052734375,
0.035247802734375,
-0.055419921875,
-0.054840087890625,
-0.0056610107421875,
-0.0... |
linhtran92/viet_vlsp | 2023-05-29T04:27:52.000Z | [
"region:us"
] | linhtran92 | null | null | 0 | 11 | 2023-05-29T03:54:01 | ---
dataset_info:
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: transcription
dtype: string
splits:
- name: train
num_bytes: 24081636306.031
num_examples: 171441
- name: validation
num_bytes: 1046661092.259
num_examples: 7501
download_size: 25080683463
dataset_size: 25128297398.289997
---
# Dataset Card for "viet_vlsp"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 528 | [
[
-0.0274810791015625,
-0.006046295166015625,
0.0238800048828125,
0.016693115234375,
-0.0254058837890625,
-0.00623321533203125,
0.019866943359375,
-0.01482391357421875,
0.054412841796875,
0.056793212890625,
-0.0506591796875,
-0.06707763671875,
-0.043609619140625,
... |
TigerResearch/tigerbot-superclue-c3-zh-5k | 2023-05-31T02:05:46.000Z | [
"license:apache-2.0",
"region:us"
] | TigerResearch | null | null | 4 | 11 | 2023-05-30T15:18:43 | ---
license: apache-2.0
---
[Tigerbot](https://github.com/TigerResearch/TigerBot) 基于cluebenchmark公开的数据集加工生成的阅读理解sft数据集
## Usage
```python
import datasets
ds_sft = datasets.load_dataset('TigerResearch/tigerbot-superclue-c3-zh-5k')
```
| 238 | [
[
-0.018524169921875,
-0.016448974609375,
0.00791168212890625,
0.0041046142578125,
-0.05169677734375,
0.002849578857421875,
0.01300048828125,
-0.00501251220703125,
0.039306640625,
0.0162353515625,
-0.05999755859375,
-0.044403076171875,
-0.00921630859375,
0.006... |
v2run/invoices-donut-data-v1 | 2023-06-15T08:31:03.000Z | [
"task_categories:feature-extraction",
"size_categories:n<1K",
"language:en",
"license:mit",
"region:us"
] | v2run | null | null | 1 | 11 | 2023-06-15T08:26:29 | ---
dataset_info:
features:
- name: image
dtype: image
- name: ground_truth
dtype: string
splits:
- name: train
num_bytes: 234024421
num_examples: 425
- name: test
num_bytes: 14512665
num_examples: 26
- name: validation
num_bytes: 27661738
num_examples: 50
download_size: 197512750
dataset_size: 276198824
license: mit
task_categories:
- feature-extraction
language:
- en
pretty_name: Sparrow Invoice Dataset
size_categories:
- n<1K
---
# Dataset Card for Invoices (Sparrow)
This dataset contains 500 invoice documents annotated and processed to be ready for Donut ML model fine-tuning.
Annotation and data preparation task was done by [Katana ML](https://www.katanaml.io) team.
[Sparrow](https://github.com/katanaml/sparrow/tree/main) - open-source data extraction solution by Katana ML.
Original dataset [info](https://data.mendeley.com/datasets/tnj49gpmtz): Kozłowski, Marek; Weichbroth, Paweł (2021), “Samples of electronic invoices”, Mendeley Data, V2, doi: 10.17632/tnj49gpmtz.2 | 1,039 | [
[
0.0006809234619140625,
-0.0107269287109375,
0.00836181640625,
0.00324249267578125,
-0.01396942138671875,
0.0021724700927734375,
0.0279541015625,
-0.0242156982421875,
0.01001739501953125,
0.05487060546875,
-0.047332763671875,
-0.038665771484375,
-0.02569580078125... |
dgslibisey/MuSiQue_subset | 2023-06-18T17:57:07.000Z | [
"region:us"
] | dgslibisey | null | null | 0 | 11 | 2023-06-18T17:49:07 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Jumtra/jglue_jnli | 2023-06-21T00:31:30.000Z | [
"region:us"
] | Jumtra | null | null | 0 | 11 | 2023-06-21T00:31:08 | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 647839
num_examples: 3079
download_size: 196877
dataset_size: 647839
---
# Dataset Card for "jglue_jnli"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 425 | [
[
-0.038177490234375,
-0.022247314453125,
0.0048675537109375,
0.010986328125,
-0.0029201507568359375,
0.00937652587890625,
0.01309967041015625,
-0.0228729248046875,
0.06890869140625,
0.0283966064453125,
-0.0533447265625,
-0.053192138671875,
-0.036834716796875,
... |
mattbit/tweet-sentiment-airlines | 2023-06-23T16:35:13.000Z | [
"region:us"
] | mattbit | null | null | 0 | 11 | 2023-06-23T16:35:05 | ---
dataset_info:
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 1359980.0
num_examples: 11712
- name: test
num_bytes: 339995.0
num_examples: 2928
download_size: 1035932
dataset_size: 1699975.0
---
# Dataset Card for "tweet-sentiment-airlines"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 466 | [
[
-0.03338623046875,
0.000011801719665527344,
0.01139068603515625,
0.039276123046875,
-0.0230255126953125,
0.01540374755859375,
0.013427734375,
0.00206756591796875,
0.07208251953125,
0.01238250732421875,
-0.07135009765625,
-0.0537109375,
-0.041778564453125,
-0... |
causal-lm/gpt4tools | 2023-06-25T03:28:01.000Z | [
"region:us"
] | causal-lm | null | null | 1 | 11 | 2023-06-25T03:27:00 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
jinmang2/ucf_crime | 2023-07-11T03:46:53.000Z | [
"region:us"
] | jinmang2 | # Real-world Anomaly Detection in Surveillance Videos
Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training.
We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work.
# Problem & Motivation
One critical task in video surveillance is detecting anomalous events such as traffic accidents, crimes or illegal activities. Generally, anomalous events rarely occur as compared to normal activities. Therefore, to alleviate the waste of labor and time, developing intelligent computer vision algorithms for automatic video anomaly detection is a pressing need. The goal of a practical anomaly detection system is to timely signal an activity that deviates normal patterns and identify the time window of the occurring anomaly. Therefore, anomaly detection can be considered as coarse level video understanding, which filters out anomalies from normal patterns. Once an anomaly is detected, it can further be categorized into one of the specific activities using classification techniques.
In this work, we propose an anomaly detection algorithm using weakly labeled training videos. That is we only know the video-level labels, i.e. a video is normal or contains anomaly somewhere, but we do not know where. This is intriguing because we can easily annotate a large number of videos by only assigning video-level labels. To formulate a weakly-supervised learning approach, we resort to multiple instance learning. Specifically, we propose to learn anomaly through a deep MIL framework by treating normal and anomalous surveillance videos as bags and short segments/clips of each video as instances in a bag. Based on training videos, we automatically learn an anomaly ranking model that predicts high anomaly scores for anomalous segments in a video. During testing, a longuntrimmed video is divided into segments and fed into our deep network which assigns anomaly score for each video segment such that an anomaly can be detected.
# Method
Our proposed approach (summarized in Figure 1) begins with dividing surveillance videos into a fixed number of segments during training. These segments make instances in a bag. Using both positive (anomalous) and negative (normal) bags, we train the anomaly detection model using the proposed deep MIL ranking loss.
https://www.crcv.ucf.edu/projects/real-world/method.png
# UCF-Crime Dataset
We construct a new large-scale dataset, called UCF-Crime, to evaluate our method. It consists of long untrimmed surveillance videos which cover 13 realworld anomalies, including Abuse, Arrest, Arson, Assault, Road Accident, Burglary, Explosion, Fighting, Robbery, Shooting, Stealing, Shoplifting, and Vandalism. These anomalies are selected because they have a significant impact on public safety. We compare our dataset with previous anomaly detection datasets in Table 1. For more details about the UCF-Crime dataset, please refer to our paper. A short description of each anomalous event is given below.
Abuse: This event contains videos which show bad, cruel or violent behavior against children, old people, animals, and women.
Burglary: This event contains videos that show people (thieves) entering into a building or house with the intention to commit theft. It does not include use of force against people.
Robbery: This event contains videos showing thieves taking money unlawfully by force or threat of force. These videos do not include shootings.
Stealing: This event contains videos showing people taking property or money without permission. They do not include shoplifting.
Shooting: This event contains videos showing act of shooting someone with a gun.
Shoplifting: This event contains videos showing people stealing goods from a shop while posing as a shopper.
Assault: This event contains videos showing a sudden or violent physical attack on someone. Note that in these videos the person who is assaulted does not fight back.
Fighting: This event contains videos displaying two are more people attacking one another.
Arson: This event contains videos showing people deliberately setting fire to property.
Explosion: This event contains videos showing destructive event of something blowing apart. This event does not include videos where a person intentionally sets a fire or sets off an explosion.
Arrest: This event contains videos showing police arresting individuals.
Road Accident: This event contains videos showing traffic accidents involving vehicles, pedestrians or cyclists.
Vandalism: This event contains videos showing action involving deliberate destruction of or damage to public or private property. The term includes property damage, such as graffiti and defacement directed towards any property without permission of the owner.
Normal Event: This event contains videos where no crime occurred. These videos include both indoor (such as a shopping mall) and outdoor scenes as well as day and night-time scenes.
https://www.crcv.ucf.edu/projects/real-world/dataset_table.png
https://www.crcv.ucf.edu/projects/real-world/method.png | @InProceedings{Sultani_2018_CVPR,
author={Sultani, Waqas and Chen, Chen and Shah, Mubarak},
title={Real-World Anomaly Detection in Surveillance Videos},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month={June},
year={2018},
} | 0 | 11 | 2023-06-30T07:00:20 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
anonymousparrot01/SubmissionData | 2023-06-30T09:23:29.000Z | [
"task_categories:fill-mask",
"task_categories:other",
"task_ids:masked-language-modeling",
"multilinguality:monolingual",
"size_categories:1M<n<10M",
"language:en",
"license:cc-by-nc-sa-4.0",
"business",
"company websites",
"region:us"
] | anonymousparrot01 | null | null | 0 | 11 | 2023-06-30T09:21:03 | ---
annotations_creators: []
language:
- en
language_creators: []
license:
- cc-by-nc-sa-4.0
multilinguality:
- monolingual
pretty_name: CompanyWeb
size_categories:
- 1M<n<10M
source_datasets: []
tags:
- business
- company websites
task_categories:
- fill-mask
- other
task_ids:
- masked-language-modeling
---
# Dataset Card for "CompanyWeb"
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [PLACEHOLDER]()
- **Repository:** [PLACEHOLDER]()
- **Paper:** [PLACEHOLDER]()
- **Leaderboard:** [PLACEHOLDER]()
- **Point of Contact:** [PLACEHOLDER]()
### Dataset Summary
The dataset contains textual content extracted from 1,788,413 company web pages of 393,542 companies. The companies included in the dataset are small, medium and large international enterprises including publicly listed companies. Additional company information is provided in form of the corresponding Standard Industry Classification (SIC) label `sic4`.
The text includes all textual information contained on the website with a timeline ranging from 2014 to 2021. The search includes all subsequent pages with links from the homepage containing the company domain name.
We filter the resulting textual data to only include English text utilizing the FastText language detection API [(Joulin et al., 2016)](https://aclanthology.org/E17-2068/).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
- en
## Dataset Structure
### Data Instances
- **#Instances:** 1789413
- **#Companies:** 393542
- **#Timeline:** 2014-2021
### Data Fields
- `id`: instance identifier `(string)`
- `cid`: company identifier `(string)`
- `text`: website text `(string)`
- `sic4`: 4-digit SIC `(string)`
### Data Splits
[PLACEHOLDER]
## Dataset Creation
### Curation Rationale
[PLACEHOLDER]
### Source Data
#### Initial Data Collection and Normalization
[PLACEHOLDER]
#### Who are the source language producers?
[PLACEHOLDER]
### Annotations
#### Annotation process
[PLACEHOLDER]
#### Who are the annotators?
[PLACEHOLDER]
### Personal and Sensitive Information
[PLACEHOLDER]
## Considerations for Using the Data
### Social Impact of Dataset
[PLACEHOLDER]
### Discussion of Biases
[PLACEHOLDER]
### Other Known Limitations
[PLACEHOLDER]
## Additional Information
### Dataset Curators
[PLACEHOLDER]
### Licensing Information
[PLACEHOLDER]
### Citation Information
```bibtex
@misc{title_year,
title={TITLE},
author={AUTHORS},
year={YEAR},
}
```
### Contributions
[PLACEHOLDER]
<!-- Thanks to [@github-username](https://github.com/<github-username>) for adding this dataset. --> | 3,695 | [
[
-0.034820556640625,
-0.039306640625,
0.00611114501953125,
0.026824951171875,
-0.02423095703125,
0.0233001708984375,
-0.01393890380859375,
-0.03863525390625,
0.0367431640625,
0.033660888671875,
-0.0699462890625,
-0.08135986328125,
-0.02886962890625,
0.0259857... |
notaphoenix/debateorg_w_effect_for_conservative_subset | 2023-10-18T12:49:27.000Z | [
"language:en",
"region:us"
] | notaphoenix | null | null | 0 | 11 | 2023-07-06T11:53:22 | ---
language: en
dataset_info:
features:
- name: text
dtype: string
- name: label
dtype: int64
- name: author
dtype: string
- name: original_text
dtype: string
- name: category
dtype: string
- name: round
dtype: int64
- name: debate_id
dtype: string
- name: idx
dtype: int64
splits:
- name: validation
num_bytes: 18498814
num_examples: 4867
- name: test
num_bytes: 9164351
num_examples: 2539
- name: training
num_bytes: 115468842
num_examples: 28802
download_size: 77817584
dataset_size: 143132007
configs:
- config_name: default
data_files:
- split: validation
path: data/validation-*
- split: test
path: data/test-*
- split: training
path: data/training-*
---
# Dataset Card for "debateorg_w_effect_for_conservative_subset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 964 | [
[
-0.05828857421875,
-0.0430908203125,
0.003215789794921875,
0.00811767578125,
-0.023956298828125,
-0.00875091552734375,
-0.005870819091796875,
-0.00402069091796875,
0.068115234375,
0.03729248046875,
-0.05450439453125,
-0.033966064453125,
-0.03448486328125,
-0... |
neural-bridge/cqa_dev | 2023-10-04T20:10:33.000Z | [
"task_categories:question-answering",
"size_categories:n<1K",
"language:en",
"region:us"
] | neural-bridge | null | null | 0 | 11 | 2023-07-06T15:36:46 | ---
task_categories:
- question-answering
language:
- en
pretty_name: s
size_categories:
- n<1K
---
# Development Dataset for Falcon-40B
This is a development dataset consisting of ten samples that are prepared on various topics. It is used for checking whether a model that is fine-tuned for the context-question-answer task can generate satisfying responses using the given context and question. | 398 | [
[
-0.07244873046875,
-0.052490234375,
-0.01111602783203125,
0.033416748046875,
0.005863189697265625,
0.020416259765625,
0.01447296142578125,
0.00206756591796875,
0.0296783447265625,
0.042236328125,
-0.08056640625,
-0.0333251953125,
-0.0113677978515625,
0.01568... |
DynamicSuperb/BirdSoundDetection_Warblrb10k | 2023-07-12T11:37:16.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 11 | 2023-07-12T06:59:13 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: label
dtype: string
- name: instruction
dtype: string
splits:
- name: test
num_bytes: 7115214099.0
num_examples: 8000
download_size: 6882889124
dataset_size: 7115214099.0
---
# Dataset Card for "bird_sound_dection_warblrb10k"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 490 | [
[
-0.05316162109375,
-0.01074981689453125,
-0.013153076171875,
0.038665771484375,
-0.01739501953125,
-0.005207061767578125,
0.01425933837890625,
-0.0272064208984375,
0.05010986328125,
0.0190277099609375,
-0.054962158203125,
-0.05194091796875,
-0.0350341796875,
... |
TrainingDataPro/spam-text-messages-dataset | 2023-09-19T19:33:39.000Z | [
"task_categories:text-classification",
"language:en",
"license:cc-by-nc-nd-4.0",
"code",
"finance",
"region:us"
] | TrainingDataPro | The SMS spam dataset contains a collection of text messages. The dataset
includes a diverse range of spam messages, including promotional offers,
fraudulent schemes, phishing attempts, and other forms of unsolicited
communication.
Each SMS message is represented as a string of text, and each entry in the
dataset also has a link to the corresponding screenshot. The dataset's content
represents real-life examples of spam messages that users encounter in their
everyday communication. | @InProceedings{huggingface:dataset,
title = {spam-text-messages-dataset},
author = {TrainingDataPro},
year = {2023}
} | 1 | 11 | 2023-07-20T10:21:02 | ---
language:
- en
license: cc-by-nc-nd-4.0
task_categories:
- text-classification
tags:
- code
- finance
dataset_info:
features:
- name: image
dtype: image
- name: text
dtype: string
splits:
- name: train
num_bytes: 4134124
num_examples: 25
download_size: 3713381
dataset_size: 4134124
---
# Spam Text Messages Dataset
The SMS spam dataset contains a collection of text messages. The dataset includes a diverse range of spam messages, including *promotional offers, fraudulent schemes, phishing attempts, and other forms of unsolicited communication*.
Each SMS message is represented as a string of text, and each entry in the dataset also has a link to the corresponding screenshot. The dataset's content represents real-life examples of spam messages that users encounter in their everyday communication.
### The dataset's possible applications:
- spam detection
- fraud detection
- customer support automation
- trend and sentiment analysis
- educational purposes
- network security
.png?generation=1689765543776590&alt=media)
# Get the dataset
### This is just an example of the data
Leave a request on [**https://trainingdata.pro/data-market**](https://trainingdata.pro/data-market?utm_source=huggingface&utm_medium=cpc&utm_campaign=spam-text-messages-dataset) to discuss your requirements, learn about the price and buy the dataset.
# Content
- **images**: includes screenshots of spam messages
- **.csv** file: contains information about the dataset
### File with the extension .csv
includes the following information:
- **image**: link to the screenshot with the spam message,
- **text**: text of the spam message
# Spam messages might be collected in accordance with your requirements.
## [TrainingData](https://trainingdata.pro/data-market?utm_source=huggingface&utm_medium=cpc&utm_campaign=spam-text-messages-dataset) provides high-quality data annotation tailored to your needs
More datasets in TrainingData's Kaggle account: **https://www.kaggle.com/trainingdatapro/datasets**
TrainingData's GitHub: **https://github.com/trainingdata-pro** | 2,254 | [
[
-0.01031494140625,
-0.05767822265625,
-0.01055908203125,
0.02764892578125,
-0.0211639404296875,
0.011932373046875,
-0.015106201171875,
-0.011749267578125,
0.0178680419921875,
0.083251953125,
-0.053253173828125,
-0.064453125,
-0.051422119140625,
-0.0044898986... |
puhsu/tabular-benchmarks | 2023-07-20T14:14:56.000Z | [
"task_categories:tabular-classification",
"task_categories:tabular-regression",
"region:us"
] | puhsu | null | null | 0 | 11 | 2023-07-20T13:56:46 | ---
task_categories:
- tabular-classification
- tabular-regression
pretty_name: tabualar-benchmarks
---
Datasets used in the paper TODO
To download the archive you could use:
```bash
wget https://huggingface.co/datasets/puhsu/tabular-benchmarks/resolve/main/data.tar
``` | 272 | [
[
-0.04559326171875,
-0.03497314453125,
0.022247314453125,
-0.0165863037109375,
-0.023406982421875,
-0.0007395744323730469,
-0.01788330078125,
-0.0213775634765625,
0.0296783447265625,
0.0362548828125,
-0.0235137939453125,
-0.033050537109375,
-0.0445556640625,
... |
andersonbcdefg/chemistry | 2023-07-21T01:24:18.000Z | [
"region:us"
] | andersonbcdefg | null | null | 2 | 11 | 2023-07-21T01:23:53 | ---
dataset_info:
features:
- name: role_1
dtype: string
- name: topic;
dtype: string
- name: sub_topic
dtype: string
- name: message_1
dtype: string
- name: message_2
dtype: string
splits:
- name: train
num_bytes: 47000178
num_examples: 20000
download_size: 21669458
dataset_size: 47000178
---
# Dataset Card for "chemistry"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 506 | [
[
-0.03216552734375,
-0.00887298583984375,
0.0438232421875,
0.004421234130859375,
0.0066680908203125,
0.0185546875,
0.01525115966796875,
-0.00455474853515625,
0.057525634765625,
0.025970458984375,
-0.06170654296875,
-0.0643310546875,
-0.02899169921875,
-0.0192... |
baber/logiqa2 | 2023-08-01T00:52:03.000Z | [
"task_categories:multiple-choice",
"language:en",
"language:zh",
"license:cc-by-sa-4.0",
"arxiv:2304.03439",
"region:us"
] | baber | The dataset is an amendment and re-annotation of LogiQA in 2020, a large-scale logical reasoning reading comprehension dataset adapted from the Chinese Civil Service Examination. We increase the data size, refine the texts with manual translation by professionals, and improve the quality by removing items with distinctive cultural features like Chinese idioms. Furthermore, we conduct a fine-grained annotation on the dataset and turn it into a two-way natural language inference (NLI) task, resulting in 35k premise-hypothesis pairs with gold labels, making it the first large-scale NLI dataset for complex logical reasoning | @ARTICLE{10174688,
author={Liu, Hanmeng and Liu, Jian and Cui, Leyang and Teng, Zhiyang and Duan, Nan and Zhou, Ming and Zhang, Yue},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
title={LogiQA 2.0 — An Improved Dataset for Logical Reasoning in Natural Language Understanding},
year={2023},
volume={},
number={},
pages={1-16},
doi={10.1109/TASLP.2023.3293046}} | 4 | 11 | 2023-07-22T20:15:28 | ---
license: cc-by-sa-4.0
task_categories:
- multiple-choice
language:
- en
- zh
pretty_name: LogiQA2.0
data_splits:
- train
- validation
- test
---
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:** https://github.com/csitfun/LogiQA2.0, https://github.com/csitfun/LogiEval
- **Repository:** https://github.com/csitfun/LogiQA2.0, https://github.com/csitfun/LogiEval
- **Paper:** https://ieeexplore.ieee.org/abstract/document/10174688
### Dataset Summary
Logiqa2.0 dataset - logical reasoning in MRC and NLI tasks
LogiEval: a benchmark suite for testing logical reasoning abilities of instruct-prompt large language models
### Licensing Information
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
### Citation Information
@ARTICLE{10174688,
author={Liu, Hanmeng and Liu, Jian and Cui, Leyang and Teng, Zhiyang and Duan, Nan and Zhou, Ming and Zhang, Yue},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
title={LogiQA 2.0 — An Improved Dataset for Logical Reasoning in Natural Language Understanding},
year={2023},
volume={},
number={},
pages={1-16},
doi={10.1109/TASLP.2023.3293046}}
@misc{liu2023evaluating,
title={Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4},
author={Hanmeng Liu and Ruoxi Ning and Zhiyang Teng and Jian Liu and Qiji Zhou and Yue Zhang},
year={2023},
eprint={2304.03439},
archivePrefix={arXiv},
primaryClass={cs.CL}
} | 1,502 | [
[
-0.0157623291015625,
-0.045745849609375,
0.024383544921875,
0.01407623291015625,
-0.01438140869140625,
-0.0200958251953125,
-0.00994873046875,
-0.03167724609375,
-0.007801055908203125,
0.0265655517578125,
-0.041168212890625,
-0.038238525390625,
-0.03515625,
... |
FreedomIntelligence/MMLU_Arabic | 2023-08-06T08:03:32.000Z | [
"language:ar",
"license:mit",
"region:us"
] | FreedomIntelligence | null | null | 0 | 11 | 2023-07-24T05:15:02 | ---
license: mit
language:
- ar
---
Arabic version of MMLU dataset translated by gpt-3.5-turbo.
The dataset is used in the research related to [MultilingualSIFT](https://github.com/FreedomIntelligence/MultilingualSIFT). | 222 | [
[
-0.0292510986328125,
-0.0312042236328125,
0.01523590087890625,
0.00969696044921875,
-0.0190582275390625,
0.01312255859375,
0.0016040802001953125,
-0.0252227783203125,
0.0128326416015625,
0.010162353515625,
-0.06268310546875,
-0.036041259765625,
-0.03741455078125... |
jondurbin/airoboros-gpt4-m2.0 | 2023-07-31T07:01:42.000Z | [
"license:other",
"region:us"
] | jondurbin | null | null | 18 | 11 | 2023-07-25T08:18:01 | ---
license: other
---
## Overview
This is a merge of https://hf.co/datasets/jondurbin/airoboros-gpt4-1.4.1 and https://hf.co/datasets/jondurbin/airoboros-gpt4-2.0
### Category breakdown
### Licence and usage restrictions
The data was generated by gpt-4 via OpenAI API calls.
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant of copyrighted or otherwise unallowable licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely idemnify me from any and all license related issues.
Attribution would be nice if you use some or all of the data. | 1,619 | [
[
-0.0219573974609375,
-0.0137481689453125,
0.0202789306640625,
0.01849365234375,
-0.0328369140625,
-0.0419921875,
-0.006076812744140625,
-0.052459716796875,
-0.00801849365234375,
0.0616455078125,
-0.0321044921875,
-0.017059326171875,
-0.04193115234375,
0.0136... |
iamtarun/code_contest_python3_alpaca | 2023-07-27T15:44:05.000Z | [
"task_categories:question-answering",
"task_categories:text2text-generation",
"task_categories:text-generation",
"size_categories:1K<n<10K",
"code",
"region:us"
] | iamtarun | null | null | 0 | 11 | 2023-07-27T15:23:10 | ---
dataset_info:
features:
- name: id
dtype: string
- name: description
dtype: string
- name: code
dtype: string
- name: test_samples
sequence:
- name: input
dtype: string
- name: output
dtype: string
- name: source
dtype:
class_label:
names:
'0': UNKNOWN_SOURCE
'1': CODECHEF
'2': CODEFORCES
'3': HACKEREARTH
'4': CODEJAM
'5': ATCODER
'6': AIZU
- name: prompt
dtype: string
splits:
- name: train
num_bytes: 624564538
num_examples: 8139
- name: valid
num_bytes: 32348022
num_examples: 95
- name: test
num_bytes: 20764786
num_examples: 122
download_size: 192319894
dataset_size: 677677346
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: valid
path: data/valid-*
- split: test
path: data/test-*
task_categories:
- question-answering
- text2text-generation
- text-generation
tags:
- code
size_categories:
- 1K<n<10K
---
# Dataset Card for Code Contest Processed
## Dataset Summary
This dataset contains coding contest questions and their solution written in Python3.
This dataset is created by processing [code_contest dataset from Deepmind](https://huggingface.co/datasets/deepmind/code_contests). It is a competitive programming dataset for machine-learning. Read more about dataset at [original source](https://huggingface.co/datasets/deepmind/code_contests).
## Columns Description
- `id` : unique string associated with a problem
- `description` : problem description
- `code` : one correct code for the problem
- `test_samples` : contains inputs and their corresponding outputs for the problem
- `source` : source of problem
- `prompt` : alpaca style generated prompt for text generation | 1,830 | [
[
-0.0263519287109375,
-0.034515380859375,
0.0186614990234375,
0.035400390625,
-0.0135040283203125,
0.0000032782554626464844,
-0.0123138427734375,
-0.00824737548828125,
0.0099945068359375,
0.048492431640625,
-0.062286376953125,
-0.057525634765625,
-0.0261993408203... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.