uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
a62d9677-e528-4e0c-a645-9feccf905f27
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other languages did they translate the data from?\n\nIntroduction\nUnderstanding the emotions expressed in a text or message is of high relevance nowadays. Companies are interested in this to get an understanding of the sentiment...
[ "English " ]
3,102
qasper
bb2dde5c-12a4-4418-9385-dd71744ff644
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what language pairs are explored?\n\nIntroduction \nThe new generation of Neural Machine Translation (NMT) systems is known to be extremely data hungry BIBREF0 . Yet, most existing NMT training pipelines fail to fully take advantage o...
[ "English-German, English-French." ]
5,626
qasper
e37aee45-b45c-4407-818b-3aa2f012c684
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the average length of the sentences?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their workforce. The PA pr...
[ "average:15.5" ]
4,196
qasper
e4c77a36-d3a6-447f-bcae-da859c58e496
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the data in CoVoST annotated for dialect?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automati...
[ "No" ]
3,601
qasper
e5cc9b76-0334-4182-84e2-3cdf7fd6eeda
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the position in the sequence part of the input?\n\nIntroduction\nOver the past few years, generating text from images and videos has gained a lot of attention in the Computer Vision and Natural Language Processing communities and s...
[ "No" ]
1,776
qasper
f8ee66c8-883b-4625-bb76-9af0810e6da3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used in evaluation?\n\nIntroduction\nThere exists a class of language construction known as pun in natural language texts and utterances, where a certain word or other lexical items are used to exploit two or more se...
[ "The homographic dataset contains 2,250 contexts, 1,607 of which contain a pun. The heterographic dataset consists of 1,780 contexts with 1,271 containing a pun." ]
3,833
qasper
1214ae86-1e8f-4b79-994d-40f53933767b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which machine learning methods are used in experiments?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively examined from d...
[ "Structural Support Vector Machine" ]
20,055
qasper
40366fed-0a73-4151-8527-e89707d70f7b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are hashtag features?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually defined as...
[ "Unanswerable" ]
2,819
qasper
42746947-201e-4160-885d-7989a08c7fa2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the state-of-the-art model for the task?\n\nIntroduction\nTable-to-text generation is an important and challenging task in natural language processing, which aims to produce the summarization of numerical table BIBREF0, BIBREF...
[ "Unanswerable" ]
6,986
qasper
43985b0f-a38e-4642-b574-1d4c4e3a9b27
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset is used in this paper?\n\nIntroduction\nUsers of photo-sharing websites such as Flickr often provide short textual descriptions in the form of tags to help others find the images. With the availability of GPS systems in c...
[ "same datasets as BIBREF7" ]
6,183
qasper
8121436a-cc89-4bdc-9d8b-3365d0c0d2cf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of this dataset?\n\nIntroduction\nSocial media is now becoming an important real-time information source, especially during natural disasters and emergencies. It is now very common for traditional news media to freque...
[ "10,898 articles, 17,794 tweets, and 13,757 crowdsourced question-answer pairs" ]
4,646
qasper
95bd5b5a-aec4-4089-9f69-c177df646b87
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many documents are in the new corpus?\n\nIntroduction\nThe automatic processing of medical texts and documents plays an increasingly important role in the recent development of the digital health area. To enable dedicated Natural ...
[ "53 documents" ]
3,590
qasper
97fbc941-e2b0-414f-9af6-e0a988a2182f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is pre-training effective in their evaluation?\n\nIntroduction\nRecently, neural machine translation (NMT) has gained popularity in the field of machine translation. The conventional encoder-decoder NMT proposed by Cho2014 uses two re...
[ "Yes" ]
3,067
qasper
ab84ac14-68af-4b03-8782-c43de069d638
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they experiment with this new dataset?\n\nIntroduction\nHow humans process language has become increasingly relevant in natural language processing since physiological data during language understanding is more accessible and reco...
[ "No" ]
4,711
qasper
ac1539df-47a8-4df4-b3a1-892ba972bc92
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much does their model outperform the state of the art results?\n\nIntroduction\nRecently, deep learning algorithms have successfully addressed problems in various fields, such as image classification, machine translation, speec...
[ "the attention model, MDREA, also outperforms the best existing research results (WAP 0.690 to 0.688)" ]
4,318
qasper
b7499d3b-e293-420c-9611-4b26e83727fa
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are models evaluated in this human-machine communication game?\n\nIntroduction\nSuppose a user wants to write a sentence “I will be 10 minutes late.” Ideally, she would type just a few keywords such as “10 minutes late” and an aut...
[ "efficiency of a communication scheme $(q_{\\alpha },p_{\\beta })$ by the retention rate of tokens, which is measured as the fraction of tokens that are kept in the keywords, accuracy of a scheme is measured as the fraction of sentences generated by greedily decoding the model that exactly matches the target senten...
2,586
qasper
bcaa137c-8575-4f79-8b3f-082b7abbf8c9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other sentence embeddings methods are evaluated?\n\nIntroduction\nIn this publication, we present Sentence-BERT (SBERT), a modification of the BERT network using siamese and triplet networks that is able to derive semantically me...
[ "GloVe, BERT, Universal Sentence Encoder, TF-IDF, InferSent" ]
5,616
qasper
c8e29402-5397-4508-aa7c-69d07edd51c5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where is a question generation model used?\n\nIntroduction\nIn recent years, there has been an increasing interest in Machine reading comprehension (MRC), which plays a vital role in the assessment of how well a machine could understa...
[ "The question generation model provides each candidate answer with a score by measuring semantic relevance between the question and the generated question based on the semantics of the candidate answer. " ]
5,578
qasper
cdb065a7-7073-42db-a02d-1327af4ebade
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used in evaluation?\n\nIntroduction\nThere exists a class of language construction known as pun in natural language texts and utterances, where a certain word or other lexical items are used to exploit two or more se...
[ "A homographic and heterographic benchmark datasets by BIBREF9." ]
3,833
qasper
d0e84153-7b0b-449a-be3d-0dc960c5d7e8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages do they use?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, including essay scoring (q...
[ "English" ]
5,705
qasper
d121d876-0610-4a61-b775-00caf57ad385
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which chinese datasets were used?\n\nIntroduction\nGrammar induction is the task of inducing hierarchical syntactic structure from data. Statistical approaches to grammar induction require specifying a probabilistic grammar (e.g. form...
[ "Answer with content missing: (Data section) Chinese with version 5.1 of the Chinese Penn Treebank (CTB)" ]
3,609
qasper
dda9a36d-2bcd-4ed5-a89a-0a0302075dd1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many humans participated?\n\nIntroduction\nMeasures of semantic similarity and relatedness quantify the degree to which two concepts are similar (e.g., INLINEFORM0 – INLINEFORM1 ) or related (e.g., INLINEFORM2 – INLINEFORM3 ). Sem...
[ "16" ]
5,721
qasper
e5399a3e-4a35-4d63-b3e0-6b0183bb83dd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they add one latent variable for each language pair in their Bayesian model?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in informatio...
[ "Yes" ]
5,277
qasper
eb08cc58-d324-4858-847f-c8dfd268c295
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is mitigation of gender bias evaluated?\n\nIntroduction\nNatural Language Processing (NLP) models are shown to capture unwanted biases and stereotypes found in the training data which raise concerns about socioeconomic, ethnic and...
[ "Using INLINEFORM0 and INLINEFORM1" ]
3,225
qasper
f28709c3-a269-43c3-8cb8-cfcd929828ad
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks do they experiment with?\n\nIntroduction\nLearning the distributed representation for long spans of text from its constituents has been a key step for various natural language processing (NLP) tasks, such as text classifica...
[ "text classification and text semantic matching" ]
6,476
qasper
f292e3ec-85f1-4ab1-a23a-030b0d26cd01
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their results on the classification and regression tasks\n\nIntroduction\n- !`Socorro, me ha picado una víbora!\n- ?`Cobra?\n- No, gratis.[5]\nGoogle Translation:\n- Help, I was bitten by a snake!\n- Does it charge?\n- Not f...
[ "F1 of 0.8099" ]
2,483
qasper
01fa5a42-a7d7-4b01-a110-c7248e1a838f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what levels of document preprocessing are looked at?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nRecent years hav...
[ "raw text, text cleaning through document logical structure detection, removal of keyphrase sparse sections of the document" ]
2,276
qasper
03b09b92-aaa0-45ea-a0cb-f44c45ad461f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which parallel corpora are used?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question answering, and other NLP...
[ "the English (EN) and German (DE) sections of the CoNLL 2009 corpus BIBREF13 , and EN-DE section of the Europarl corpus BIBREF14 " ]
5,269
qasper
076d70b4-3772-46da-9de5-c437893583c7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the interpretability merits of the approach demonstrated?\n\nIntroduction\nEvent detection on microblogging platforms such as Twitter aims to detect events preemptively. A main task in event detection is detecting events of pr...
[ "directly solicits informative keywords from the crowd for model training, thereby providing human-understandable explanations for the improved model" ]
6,677
qasper
08f7a9eb-dfcb-45d4-9a49-218703346e8f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments were carried out on the corpus?\n\nIntroduction\n“Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various languages, c...
[ "task of humor identification in social media texts is analyzed as a classification problem" ]
3,610
qasper
0f16b2cb-ace0-4fc4-8f1c-0cb01c6867d0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the LSTM baseline a sub-word model?\n\nIntroduction\nLanguage modeling is a probabilistic description of language phenomenon. It provides essential context to distinguish words which sound similar and therefore has one of the most ...
[ "Yes" ]
2,735
qasper
171bf465-0062-403c-bb64-2c0528d98c49
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of the baseline?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding systems for political science, opinion rese...
[ "75.1% and 75.6% accuracy" ]
4,998
qasper
284f604f-543a-4fc4-bcb8-beff43d218fb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they build a model to automatically detect demographic, lingustic or psycological dimensons of people?\n\nIntroduction\nBlogging gained momentum in 1999 and became especially popular after the launch of freely available, hosted pla...
[ "No" ]
1,948
qasper
36fe9ed7-bf1e-4cce-a132-0bb298b0bba9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural language processing. Early such systems were mostly built using markup language...
[ "Unanswerable" ]
8,579
qasper
48455f4f-4a87-4a64-bcad-9be6d737408c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What state-of-the-art deep neural network is used?\n\nIntroduction\nNamed entity recognition (NER) is a challenging problem in Natural Language Processing, and often serves as an important step for many popular applications, such as i...
[ "BIBREF15, BIBREF19, BIBREF20 " ]
2,384
qasper
5b946674-7c2a-4730-a42c-58ad1b6b7b01
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What state-of-the-art results are achieved?\n\nIntroduction\nThere exists a class of language construction known as pun in natural language texts and utterances, where a certain word or other lexical items are used to exploit two or m...
[ "for the homographic dataset F1 score of 92.19 and 80.19 on detection and location and for the heterographic dataset F1 score of 89.76 on detection" ]
3,835
qasper
66cc78d2-1e13-4a4b-ab0f-3fae1c0a867a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the discriminator's reward made available at each step to the generator?\n\nIntroduction\nNatural text generation, as a key task in NLP, has been advanced substantially thanks to the flourish of neural models BIBREF0 , BIBREF1 . Ty...
[ "Unanswerable" ]
5,225
qasper
70377a1a-a41e-446e-97c8-e407e61523f1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines are used for comparison?\n\nIntroduction\nKnowledge graphs have been proved to benefit many artificial intelligence applications, such as relation extraction, question answering and so on. A knowledge graph consists of ...
[ "TransE" ]
5,214
qasper
7135b6c3-76f6-4970-8b89-2d1e49148d71
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used?\n\nIntroduction\nThe concept of message passing over graphs has been around for many years BIBREF0, BIBREF1, as well as that of graph neural networks (GNNs) BIBREF2, BIBREF3. However, GNNs have only recently s...
[ " Reuters, BBCSport BIBREF30, Polarity BIBREF31, Subjectivity BIBREF32, MPQA BIBREF33, IMDB BIBREF34, TREC BIBREF35, SST-1 BIBREF36, SST-2 BIBREF36, Yelp2013 BIBREF26" ]
6,272
qasper
75fd784d-f431-4fce-9be1-38848f675018
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the student reflection data very different from the newspaper data? \n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, B...
[ "Yes" ]
5,016
qasper
81285a3f-fdff-4a75-b34e-e0f92fb47263
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which deep learning architecture do they use for sentence segmentation?\n\nIntroduction\nAutomatic summarization, machine translation, question answering, and semantic parsing operations are useful for processing, analyzing, and extra...
[ "Bi-LSTM-CRF" ]
9,317
qasper
82e3b78f-0663-48f2-9b81-65c8a187dedd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what civil field is the dataset about?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with civil law sy...
[ "divorce" ]
5,476
qasper
95e189cc-cbca-4d71-aed3-e0c274283779
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the components of the general knowledge learning engine?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural language processing. Early such systems were mostly built ...
[ "Answer with content missing: (list)\nLiLi should have the following capabilities:\n1. to formulate an inference strategy for a given query that embeds processing and interactive actions.\n2. to learn interaction behaviors (deciding what to ask and when to ask the user).\n3. to leverage the acquired knowledge in th...
8,581
qasper
9f724a41-0121-4ffb-ab21-6f7a4f83aa61
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which models did they experiment with?\n\nIntroduction\nIn the field of natural language processing (NLP), the most prevalent neural approach to obtaining sentence representations is to use recurrent neural networks (RNNs), where word...
[ "Stacked LSTMs, Cell-aware Stacked LSTMs, Sentence Encoders, Top-layer Classifiers" ]
4,500
qasper
a9b49844-4660-4110-a253-47709fec48c7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they combine a deep learning model with a knowledge base?\n\nIntroduction\nNamed entity recognition (NER) BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 is the process by which we identify text spans which mention named entities, and to...
[ "Entities from a deep learning model are linked to the related entities from a knowledge base by a lookup." ]
3,161
qasper
af006092-3b98-41c5-8759-296dcafcdcfd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which architecture do they use for the encoder and decoder?\n\nIntroduction\nConventional large-vocabulary continuous speech recognition (LVCSR) systems typically perform multi-level pattern recognition tasks that map the acoustic spe...
[ "we construct an encoder with several convolutional layers BIBREF14 followed by NIN layers BIBREF15 as the lower part in the encoder and integrate them with deep bidirectional long short-term memory (Bi-LSTM) BIBREF16 at the higher part, On the decoder side, we use a standard deep unidirectional LSTM with global at...
3,657
qasper
b6a5b1d4-663c-4c21-befe-3fb88458ff2d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do their results compare to state-of-the-art?\n\nIntroduction\nIn this digital era, online discussions and interactions has become a vital part of daily life of which a huge part is covered by social media platforms like twitter, ...
[ "Unanswerable" ]
3,371
qasper
bd654884-bc0e-44f3-bde3-869e2f1cccf9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of celebrities do they obtain tweets from?\n\nIntroduction\nSocial media platforms, particularly microblogging services such as Twitter, have become increasingly popular BIBREF0 as a means to express thoughts and opinions. T...
[ "Amitabh Bachchan, Ariana Grande, Barack Obama, Bill Gates, Donald Trump,\nEllen DeGeneres, J K Rowling, Jimmy Fallon, Justin Bieber, Kevin Durant, Kim Kardashian, Lady Gaga, LeBron James,Narendra Modi, Oprah Winfrey" ]
5,282
qasper
dde13a33-336a-4a96-a5a2-80cb5b15692b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What future possible improvements are listed?\n\nIntroduction\nKnowledge and/or data is often modeled in a structure, such as indexes, tables, key-value pairs, or triplets. These data, by their nature (e.g., raw data or long time-seri...
[ "to further constrain the model on the data structure in order to prevent inaccurate of even contradictory descriptions" ]
7,007
qasper
fef222a2-ff1e-4214-ae4d-cbc559c36099
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the interannotator agreement for the human evaluation?\n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2. Ho...
[ "Unanswerable" ]
5,015
qasper
ff5e0535-7007-47f0-86d7-3d6cddb54278
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is best performing model among author's submissions, what performance it had?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social me...
[ "For SLC task, the \"ltuorp\" team has the best performing model (0.6323/0.6028/0.6649 for F1/P/R respectively) and for FLC task the \"newspeak\" team has the best performing model (0.2488/0.2863/0.2201 for F1/P/R respectively)." ]
2,443
qasper
075f046b-bf62-40c5-8e46-cb1b1fea8740
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the quality of singing voice measured?\n\nIntroduction\nSinging is an important way of human expression and the techniques of singing synthesis have broad applications in different prospects including virtual human, movie dubbi...
[ "To compare the conversions between USVC and PitchNet, we employed an automatic evaluation score and a human evaluation score." ]
2,969
qasper
13be15f9-e267-475d-99b6-a1f2276b4b5e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the industry classes defined in this paper?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who thei...
[ "technology, religion, fashion, publishing, sports or recreation, real estate, agriculture/environment, law, security/military, tourism, construction, museums or libraries, banking/investment banking, automotive" ]
5,300
qasper
24831767-ad4a-4d12-bffd-81b555090389
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the score of the proposed model?\n\nIntroduction\nQuestion answering (QA) has drawn a lot of attention in the past few years. QA tasks on images BIBREF0 have been widely studied, but most focused on understanding text documen...
[ "Best results authors obtain is EM 51.10 and F1 63.11" ]
3,115
qasper
25512fb0-5853-422e-9465-0fc2577aa479
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper report the performance of the model for each individual language?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding sys...
[ "Yes" ]
5,004
qasper
29f83438-beed-4e9e-ac2e-1af5960dab82
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/ Deep neural networks have been widely used in ...
[ "SVM with unigram, bigram, trigram features, with average word embedding, with average transformed word embeddings, CNN and RCNN, SVM, CNN, RCNN with comment information" ]
5,895
qasper
35a5a946-ec3c-4053-8572-2a8dcf848ade
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they use a crowdsourcing platform for annotations?\n\nIntroduction\nThe focus of the word sense disambiguation (WSD) task is polysemy, i.e. words having several substantially different meanings. Two common examples are bank (river...
[ "Unanswerable" ]
4,990
qasper
3baeb947-6863-433b-b300-a56c57f88b67
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they match words before reordering them?\n\nIntroduction\nDeep Learning approaches have achieved impressive results on various NLP tasks BIBREF0 , BIBREF1 , BIBREF2 and have become the de facto approach for any NLP task. Howeve...
[ "Unanswerable" ]
2,977
qasper
3d411b05-3f33-4029-b5f5-7b230dd64aa2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines do they introduce?\n\nIntroduction\nThe automatic processing of medical texts and documents plays an increasingly important role in the recent development of the digital health area. To enable dedicated Natural Language...
[ "Conditional Random Fields, BiLSTM-CRF, Multi-Task Learning, BioBERT" ]
3,588
qasper
4002bf18-f219-4d7a-8fa6-22b17dc0ea51
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper report the performance of the model for each individual language?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding sys...
[ "Yes" ]
5,004
qasper
44091d3a-b2d8-45fb-9fec-577f197de834
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which representation learning architecture do they adopt?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic representation of tweets can...
[ "Unanswerable" ]
2,508
qasper
525cb351-f840-48ab-8ddd-8bd072caa8ba
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What interface does Macaw currently have?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy...
[ "File IO, Standard IO, Telegram" ]
2,271
qasper
570f282e-b195-445f-9e4b-53816fb81aab
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what accents are present in the corpus?\n\nIntroduction\nNowadays deep learning techniques outperform the other conventional methods in most of the speech-related tasks. Training robust deep neural networks for each task depends on th...
[ "Unanswerable" ]
5,099
qasper
67ab2e4c-3bf2-4816-ad06-bc0a7075e499
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which data do they use as a starting point for the dialogue dataset?\n\nProblem Statement\nSpoken conversations still remain the most natural and effortless means of human communication. Thus a lot of valuable information is conveyed ...
[ "A sample from nurse-initiated telephone conversations for congestive heart failure patients undergoing telepmonitoring, post-discharge from the Health Management Unit at Changi General Hospital" ]
4,633
qasper
995fc6f4-2969-4e45-9f1b-528f1fb0a36e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which toolkits do they use?\n\nIntroduction\nAs social media, specially Twitter, takes on an influential role in presidential elections in the U.S., natural language processing of political tweets BIBREF0 has the potential to help wit...
[ "BIBREF17, BIBREF18, TensiStrength BIBREF13, TwitterNLP BIBREF6, BIBREF19, CogComp-NLP BIBREF20, Stanford NLP NER BIBREF21" ]
2,135
qasper
a18c8164-c7ad-4b89-aa2c-66555edd7193
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What GAN models were used as baselines to compare against?\n\nIntroduction\nNatural text generation, as a key task in NLP, has been advanced substantially thanks to the flourish of neural models BIBREF0 , BIBREF1 . Typical frameworks ...
[ "MLE, SeqGAN, LeakGAN, MaliGAN, IRL, RAML, DialogGAN, DPGAN" ]
5,224
qasper
a1f7b5b1-2fa2-4a3c-810d-83f1582b16df
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much data samples do they start with before obtaining the initial model labels?\n\nIntroduction\nState-of-the-art automatic speech recognition (ASR) systems BIBREF0 have large model capacities and require significant quantities of...
[ "1,700-hour ( INLINEFORM2 1.1M instances) unlabeled dataset" ]
2,240
qasper
a2f6cb15-cbd6-4bc5-bbe2-d138cdf25862
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they extend LAMA evaluation framework to focus on negation?\n\nIntroduction\nPretrained language models like Transformer-XL BIBREF1, ELMo BIBREF2 and BERT BIBREF3 have emerged as universal tools that capture a diverse range of...
[ "To this end, we introduce the negated LAMA dataset. We construct it by simply inserting negation elements (e.g., “not”) in LAMA cloze statement" ]
1,840
qasper
a70aa60c-a1d1-481b-a31f-bca0f15179e0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the three steps to feature elimination?\n\nIntroduction\nIn recent years, there has been a movement to leverage social medial data to detect, estimate, and track the change in prevalence of disease. For example, eating disord...
[ "Reduction, Selection, Rank" ]
2,801
qasper
b2be1bb7-3856-495a-b810-43d17a9850d2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the model evaluated on NLG datasets or dialog datasets?\n\nIntroduction\nNatural Language Generation (NLG) plays a critical role in Spoken Dialogue Systems (SDS) with task is to convert a meaning representation produced by the Di...
[ "NLG datasets" ]
5,823
qasper
b2fe5f9b-ebaf-43f9-9a02-6cd3c8ff6743
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What learning models are used on the dataset?\n\nIntroduction\nAbusive language refers to any type of insult, vulgarity, or profanity that debases the target; it also can be anything that causes aggravation BIBREF0 , BIBREF1 . Abusive...
[ "Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Random Forests (RF), Gradient Boosted Trees (GBT), CNN, RNN" ]
2,920
qasper
b91303e7-b412-49ae-9c55-3daf300d4d56
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What NLP tasks do they consider?\n\nIntroduction\nWe posses a wealth of prior knowledge about many natural language processing tasks. For example, in text categorization, we know that words such as NBA, player, and basketball are stro...
[ "text classification for themes including sentiment, web-page, science, medical and healthcare" ]
4,999
qasper
b96bcdd6-4a95-4948-9bae-82b9f50af4f2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks did they use to evaluate performance for male and female speakers?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous studies have been conducted in...
[ "Unanswerable" ]
5,381
qasper
bbc86f9c-63a3-4cc0-9140-74bc9b890542
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the quality of the data empirically evaluated? \n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascadin...
[ "Validated transcripts were sent to professional translators., various sanity checks to the translations, sanity check the overlaps of train, development and test sets" ]
3,602
qasper
bc4a2ea2-5329-4d2f-88a4-ad5276028ffb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are their results on the constructed dataset?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with ...
[ "AutoJudge consistently and significantly outperforms all the baselines, RC models achieve better performance than most text classification models (excluding GRU+Attention), Comparing with conventional RC models, AutoJudge achieves significant improvement" ]
5,477
qasper
c354c63c-24ae-4099-b272-64dcde64d0c5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the new dataset?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most common ...
[ "Unanswerable" ]
3,086
qasper
c4729bcb-b0a4-48ad-a2cd-11d13cf2c7b7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they study numerical properties of their obtained vectors (such as orthogonality)?\n\nIntroduction\nNumerous lexical semantic properties are captured by representations encoding distributional properties of words, as has been demon...
[ "No" ]
5,406
qasper
c938d0e3-2a34-441e-9583-9d702cc4cdc5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is order of \"words\" important in car speak language?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer...
[ "No" ]
2,208
qasper
ef7084b0-b312-4419-a804-180d95e25049
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which variation provides the best results on this dataset?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassm...
[ "Projected Layer" ]
3,868
qasper
0b35e791-82f6-4591-b285-f23ca09a4b45
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they split text to obtain sentence levels?\n\nIntroduction\nMany machine learning models in question answering tasks often involve matching mechanism. For example, in factoid question answering such as SQuAD BIBREF1 , one needs...
[ "Unanswerable" ]
3,272
qasper
2035a403-6e27-4140-b754-16d22e5ed734
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the characteristics of the accounts that spread fake news?\n\n10pt\n1.10pt\n[ Characterizing Political Fake News in Twitter by its Meta-DataJulio Amador Díaz LópezAxel Oehmichen Miguel Molina-Solana( j.amador, axelfrancois.oe...
[ "have a larger proportion of friends/followers (i.e. they have, on average, the same number of friends but a smaller number of followers) than those spreading viral content only" ]
3,932
qasper
3eb15588-07cd-4087-86b5-7042e914da09
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What aspects of discussion are relevant to instructor intervention, according to the attention mechanism?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quali...
[ "context inference" ]
4,784
qasper
424e4d1c-e7f3-4965-a6b7-41cb41aa2f2c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use large or small BERT?\n\nIntroduction\nWord Sense Disambiguation (WSD) is a fundamental task and long-standing challenge in Natural Language Processing (NLP), which aims to find the exact sense of an ambiguous word in a par...
[ "small BERT" ]
3,003
qasper
58051a5d-24cd-474a-bb6b-d70cf6ea04bb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What transfer learning tasks are evaluated?\n\nIntroduction\nIn this publication, we present Sentence-BERT (SBERT), a modification of the BERT network using siamese and triplet networks that is able to derive semantically meaningful s...
[ "MR: Sentiment prediction for movie reviews snippets on a five start scale BIBREF25.\n\nCR: Sentiment prediction of customer product reviews BIBREF26.\n\nSUBJ: Subjectivity prediction of sentences from movie reviews and plot summaries BIBREF27.\n\nMPQA: Phrase level opinion polarity classification from newswire BIB...
5,615
qasper
5f32a057-47cc-4930-b9c9-5c327da60eda
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline used?\n\nIntroduction\nWriting errors can occur in many different forms – from relatively simple punctuation and determiner errors, to mistakes including word tense and form, incorrect collocations and erroneous ...
[ "error detection system by Rei2016" ]
2,710
qasper
6387ecc8-30d9-4dc8-8f41-1aff9fc1abd7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building blocks in the course of algor...
[ "Unanswerable" ]
8,083
qasper
67bdacde-7bb6-4c5a-9036-33b8197b681d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quality education from reputed universities to students at large. ...
[ "Unanswerable" ]
4,777
qasper
6f31dd69-93a8-447d-998f-b5138f345f07
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much does their best model outperform the state-of-the-art?\n\nIntroduction\nRelation classification is the task of assigning sentences with two marked entities to a predefined set of relations. The sentence “We poured the <e1>...
[ "0.8% F1 better than the best state-of-the-art" ]
3,324
qasper
80ea4609-af44-4944-aac5-cc08704ea456
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many electrodes were used on the subject in EEG sessions?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIBREF0 , BIBREF...
[ "Unanswerable" ]
3,285
qasper
817d8464-d070-4154-86d8-1e83c4c39b5d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they collected the two datasets?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/ Deep neural networks have been wi...
[ "No" ]
5,896
qasper
88d3598c-361a-4b5f-90ac-de572afabc8c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they define similar equations?\n\nIntroduction\nEquations are an important part of scientific articles, but many existing machine learning methods do not easily handle them. They are challenging to work with because each is uni...
[ "By using Euclidean distance computed between the context vector representations of the equations" ]
3,789
qasper
908e7291-8faf-4cf2-9b77-008124cec687
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What embedding techniques are explored in the paper?\n\nIntroduction\nMeasures of semantic similarity and relatedness quantify the degree to which two concepts are similar (e.g., INLINEFORM0 – INLINEFORM1 ) or related (e.g., INLINEFOR...
[ "Skip–gram, CBOW" ]
5,725
qasper
90b28332-4f98-429e-9d2d-244c76d3b5d9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate only on English datasets?\n\nIntroduction\nIn recent years, there has been a movement to leverage social medial data to detect, estimate, and track the change in prevalence of disease. For example, eating disorders in...
[ "Yes" ]
2,800
qasper
9e714bf3-2d6b-4d5c-b83e-1235b0e770d3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which fonts are the best indicators of high quality?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, in...
[ "Unanswerable" ]
5,709
qasper
ac925070-4f63-408f-8a47-5c27f5a9efeb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they used dataset from another domain for evaluation?\n\nIntroduction\nHeadline generation is the process of creating a headline-style sentence given an input article. The research community has been regarding the task of headline...
[ "No" ]
6,348
qasper
d47afbb8-3ff4-4f13-a25e-0a255deaf4ee
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why does the proposed task a good proxy for the general-purpose sequence to sequence tasks?\n\nIntroduction\nIt is well known that language has certain structural properties which allows natural language speakers to make “infinite use...
[ "The task is set up to mimic (albeit, in an oversimplified manner) the input-output symbol alignments and local syntactic properties that models must learn in many natural language tasks, such as translation, tagging and summarization." ]
2,573
qasper
d555d036-55e5-4dfe-82c8-de1ba95c9068
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they remove seasonality from the time series?\n\nIntroduction\nEarlier studies on stock market prediction are based on the historical stock prices. Later studies have debunked the approach of predicting stock market movements using...
[ "No" ]
3,164
qasper
d8169eaa-65ff-46a5-8f43-a24b3363a01b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What additional features and context are proposed?\n\nIntroduction\nAbusive language refers to any type of insult, vulgarity, or profanity that debases the target; it also can be anything that causes aggravation BIBREF0 , BIBREF1 . Ab...
[ "text sequences of context tweets" ]
2,919
qasper
e0dfdf1e-8928-4315-a59b-3ee63ed73f66
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What criteria are used to select the 8,640 English sentences?\n\nIntroduction\n[0]leftmargin=* [0]leftmargin=*\nAutomatic systems have had a significant and beneficial impact on all walks of human life. So much so that it is easy to o...
[ "Sentences involving at least one race- or gender-associated word, sentence have to be short and grammatically simple, sentence have to include expressions of sentiment and emotion." ]
6,032
qasper
e2b45942-93c9-4785-a971-212f166106da
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which component has the greatest impact on performance?\n\nIntroduction\nThe concept of message passing over graphs has been around for many years BIBREF0, BIBREF1, as well as that of graph neural networks (GNNs) BIBREF2, BIBREF3. How...
[ "Removing the master node deteriorates performance across all datasets" ]
6,276
qasper