uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
ec56d5a2-75fd-4948-a8b2-7ad9b687d5f4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which classifiers are evaluated?\n\nIntroduction\nTask-oriented dialog systems have become ubiquitous, providing a means for billions of people to interact with computers using natural language. Moreover, the recent influx of platform...
[ "SVM, MLP, FastText, CNN, BERT, Google's DialogFlow, Rasa NLU" ]
3,153
qasper
eff2461c-b5c6-4e73-939e-a0823171e2b0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the dataset?\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to train and evaluate neural network models that generate...
[ "30,000" ]
2,927
qasper
f121a8df-d345-49ee-b5eb-2885db5f7044
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their decoder generate text?\n\nIntroduction\nConventional large-vocabulary continuous speech recognition (LVCSR) systems typically perform multi-level pattern recognition tasks that map the acoustic speech waveform into a hi...
[ "decoder task, which predicts the target sequence probability at time INLINEFORM3 based on previous output and context information" ]
3,653
qasper
fd940a7e-625f-4431-bc91-bc3c88eb1198
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is dataset of 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 listens and ...
[ "$3,209$ reviews about 553 different cars from 49 different car manufacturers" ]
2,206
qasper
fea4b8e9-a528-4df8-bd19-6de5827445ad
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what corpus is used to learn behavior?\n\nIntroduction\nSpoken Dialogue Systems (SDS) allow human-computer interaction using natural speech. Task-oriented dialogue systems, the focus of this work, help users achieve goals such as find...
[ "The manual transcriptions of the DSTC2 training set " ]
6,341
qasper
091001a0-9fc8-4e68-8a8d-8686ec040dd0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What summarization algorithms did the authors experiment with?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their wo...
[ "LSA, TextRank, LexRank" ]
4,197
qasper
0af76b91-d116-4dbe-a31f-48dd4c560c85
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages are the model transferred to?\n\nIntroduction\nPre-trained models BIBREF0, BIBREF1 have received much of attention recently thanks to their impressive results in many down stream NLP tasks. Additionally, multilingual pr...
[ "French (fr), Russian (ru), Arabic (ar), Chinese (zh), Hindi (hi), and Vietnamese (vi)" ]
5,301
qasper
2474a977-9bf8-49fd-8e57-8c26a6cfc9ea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the three regularization terms?\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 ...
[ "a regularization term associated with neutral features, the maximum entropy of class distribution regularization term, the KL divergence between reference and predicted class distribution" ]
4,998
qasper
26fe174d-009f-4d99-8695-6775c50c4498
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does final model rate on Likert scale?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and dry captions which are...
[ "average content score across the paintings is 3.7, average creativity score is 3.9, average style score is 3.9 " ]
2,140
qasper
2d1b8a0e-4c7f-4e55-99ef-5017c9d48e37
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of their dataset?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people ass...
[ "13,939" ]
5,795
qasper
2df36db1-38f3-47f9-ad02-6e800252b06c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used?\n\nIntroduction\nNeural machine translation (NMT) has gained a lot of attention recently due to its substantial improvements in machine translation quality achieving state-of-the-art performance for several lan...
[ "RWTH German-English dataset" ]
4,374
qasper
3f54c513-a824-42ad-a5a7-77b2127ca9da
[{"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...
[ "15.5" ]
4,196
qasper
40970f48-4f5e-4f34-8a4e-0e62dd0d8a1c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the previous state of the art?\n\nIntroduction\nOther than encoder-only pretrained transformer architectures BIBREF2, BIBREF3, BIBREF4, encoder–decoder style pretrained transformers BIBREF0, BIBREF5 have been proven to be effe...
[ "RoBERTa" ]
1,830
qasper
4abca96c-84e5-4419-9b0a-f401e9f63ac9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is \"propaganda\" defined for the purposes of this study?\n\nIntroduction\nThe challenges of imbalanced classification—in which the proportion of elements in each class for a classification task significantly differ—and of the abi...
[ "First, propaganda is a social phenomenon and takes place as an act of communication BIBREF19, and so it is more than a simple information-theoretic message of zeros and ones—it also incorporates an addresser and addressee(s), each in phatic contact (typically via broadcast media), ideally with a shared denotationa...
5,829
qasper
5e7ec8cc-68c6-4533-974f-d1be64237ca7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the message passing framework?\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 o...
[ "It is a framework used to describe algorithms for neural networks represented as graphs. Main idea is that that representation of each vertex is updated based on messages from its neighbors." ]
6,274
qasper
60e49dd3-43a6-4163-bd27-b3234b35870e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Were any of these tasks evaluated in any previous work?\n\nIntroduction\nThe recently introduced BERT model BIBREF0 exhibits strong performance on several language understanding benchmarks. To what extent does it capture syntax-sensit...
[ "Yes" ]
1,990
qasper
60f4acea-9883-4781-aa4c-94babe2fd51c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the state-of-the-art models?\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 sys...
[ "SVM , CNN , GRU , CNN/GRU+law, r-net , AoA " ]
5,477
qasper
65661c9e-d4e1-402d-b6c3-f208a54a7dd6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"did they compare with other extractive summarization methods?\n\nIntroduction\nSummarization of patient information is essential to the practice of medicine. Clinicians must synthesize information from diverse data sources to communic...
[ "No" ]
3,950
qasper
7a110e88-aa93-40e5-8a7c-f156bcbe3799
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Up to how many samples do they experiment with?\n\nIntroduction\nDeep neural networks (DNNs), in particular convolutional and recurrent neural networks, with huge architectures have been proven successful in wide range of tasks includ...
[ "535" ]
4,146
qasper
a83ec140-117f-4028-9362-857c26614d18
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which multilingual approaches do they compare with?\n\nIntroduction\nAlthough Neural Machine Translation (NMT) has dominated recent research on translation tasks BIBREF0, BIBREF1, BIBREF2, NMT heavily relies on large-scale parallel da...
[ "BIBREF19, BIBREF20" ]
5,434
qasper
a8962aaa-cd1f-42cc-950b-5bf063a829e3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\n\nIntroduction\nAccurate grapheme-to-phoneme conversion (g2p) is important for any application that depends on the sometimes inconsistent relationship between spoken and written language. Most prominently, this...
[ "system presented by deri2016grapheme" ]
4,275
qasper
a8b053b0-abf8-45b3-bc24-dbec9cb0cd8f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the dataset feature only English language data?\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 . ...
[ "Yes" ]
2,920
qasper
b8bbd4d5-47d2-4919-9161-3d13391fb65a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they obtain the new context represetation?\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>milk</e1> into th...
[ "They use two independent convolutional and max-pooling layers on (1) a combination of the left context, the left entity and the middle context; and (2) a combination of the middle context, the right entity and the right context. They concatenated the two results after pooling to get the new context representation....
3,320
qasper
bb9ee81e-8cdf-4e57-a06b-62e753fd2db4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why is lemmatization not necessary in English?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems. The most well-known examples of...
[ "Advanced neural architectures and contextualized embedding models learn how to handle spelling and morphology variations." ]
4,024
qasper
ddd4bf21-3a54-4ad6-837f-c8929d29089f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the method achieve sota performance on this dataset?\n\nIntroduction\nThe development of online peer-to-peer markets in the 1990s, galvanized by the launch of sites like eBay, fundamentally shifted the way buyers and sellers coul...
[ "No" ]
3,510
qasper
ed47a72f-2708-440c-958f-7f3f0beeeab9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What TIMIT datasets are used for testing?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Word2Vec BIBREF0 and GloveBIBREF1. The re...
[ "Once split into 8 subsets (A-H), the test set used are blocks D+H and blocks F+H" ]
5,207
qasper
edaaecec-4226-4233-b5fd-f206f12967cf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was annotation performed?\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 Pro...
[ "WebAnno" ]
3,586
qasper
ee6d5e11-f5e1-4924-8fbd-3ff03dd35317
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"For how many probe tasks the shallow-syntax-aware contextual embedding perform better than ELMo’s embedding?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextu...
[ "3" ]
3,693
qasper
f086f905-a698-4e09-8d84-4f490b12550b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Overall, does having parallel data improve semantic role induction across multiple languages?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability...
[ "No" ]
5,276
qasper
f40057d2-eab7-4558-b308-561da6e033dd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is NER?\n\nIntroduction\nThe explosion of available scientific articles in the Biomedical domain has led to the rise of Biomedical Information Extraction (BioIE). BioIE systems aim to extract information from a wide spectrum of a...
[ "Named Entity Recognition" ]
3,928
qasper
fc960c61-9581-48a4-82f9-776a0df999f0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is their MNER SnapCaptions dataset?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opinions and preferences of groups and individuals. These insights are pr...
[ "10K user-generated image (snap) and textual caption pairs" ]
5,443
qasper
00a12750-da15-4f7e-b80e-b1d3b7acf9a0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were the evaluation metrics?\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...
[ "Unlabeled sentence-level F1, perplexity, grammatically judgment performance" ]
3,609
qasper
0a926ccc-55e8-4359-9e07-8694d1d7fba2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is this dataset publicly available for commercial use?\n\nIntroduction and Related Work\nWith the widespread adoption of electronic health records (EHRs), medical data are being generated and stored digitally in vast quantities BIBREF...
[ "No" ]
2,184
qasper
0fb46cf4-a9cb-48c1-bf95-f05b9afd9d40
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is future work planed?\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 generation as a summarization...
[ "ethical questions about generating sensational headlines, which can be further explored, improving the sensationalism scorer, investigating the applications of dynamic balancing methods between RL and MLE" ]
6,345
qasper
106395d8-4b3c-495a-93f7-37dc5c57c386
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large are the textual descriptions of entities?\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 ...
[ "Unanswerable" ]
5,215
qasper
1587d946-0db5-4fe4-9d00-193399de866a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does BERT reach the best performance among all the algorithms compared?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data...
[ "No" ]
6,156
qasper
1b0c2e00-86f8-4f23-bf9c-55ecc17df4de
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which Facebook pages did they look at?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nIn the spirit of the brevity o...
[ "FoxNews, CNN, ESPN, New York Times, Time magazine, Huffington Post Weird News, The Guardian, Cartoon Network, Cooking Light, Home Cooking Adventure, Justin Bieber, Nickelodeon, Spongebob, Disney" ]
4,373
qasper
41667938-d8b5-444d-8e3e-b352a195b6bf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is SemCor3.0 reflective of English language data in general?\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 o...
[ "Yes" ]
3,008
qasper
48e11d95-5cc0-4322-a3f0-afc055329240
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they perform error analysis?\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, facebook, instagra...
[ "No" ]
3,366
qasper
58095178-1939-4f59-b3b9-9d400d0c4d30
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were their performance results?\n\nIntroduction\nMedical search engines are an essential component for many online medical applications, such as online diagnosis systems and medical document databases. A typical online diagnosis ...
[ " the hybrid NER model achieved a F1 score of $0.995$ on synthesized queries and $0.948$ on clinical notes while the i2b2 NER model achieved a F1 score of $0.441$ on synthesized queries and $0.927$ on clinical notes" ]
4,884
qasper
5a876a4d-7f1c-4090-9c6e-ac9316e2aa21
[{"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
6784d0b2-93ed-4b17-892f-5eb514c9c0c8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset(s) do they experiment with?\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. However, the...
[ "IITB English-Hindi parallel corpus, ILCI English-Hindi parallel corpus" ]
2,976
qasper
7976b0ce-5e4b-45ad-bfae-280dfa80e7ce
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What modern MRC gold standards are analyzed?\n\nIntroduction\nThere is a recent spark of interest in the task of Question Answering (QA) over unstructured textual data, also referred to as Machine Reading Comprehension (MRC). This is ...
[ "fit our problem definition and were published in the years 2016 to 2019, have at least $(2019 - publication\\ year) \\times 20$ citations" ]
6,561
qasper
9080a7b4-ac9c-4878-bba6-dbeb0af0238c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the benchmark attacking methods?\n\nIntroduction\nAdversarial examples, a term introduced in BIBREF0, are inputs transformed by small perturbations that machine learning models consistently misclassify. The experiments are co...
[ "FGM, FGVM, DeepFool BIBREF5, HotFlip BIBREF3) and TYC BIBREF4" ]
6,095
qasper
9b65c43b-07a4-423f-8608-8a332224def4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they obtain the lexicon?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known then the ap...
[ "Unanswerable" ]
2,610
qasper
a0b05044-7ac5-43c4-be69-0cd855621c00
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Were any of the pipeline components based on deep learning models?\n\nIntroduction\nThe automatic identification, extraction and representation of the information conveyed in texts is a key task nowadays. In fact, this research topic ...
[ "No" ]
3,010
qasper
b19849d0-4710-491c-8551-774d4c59f82a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why is the adversarial setting appropriate for misspelling recognition?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the ...
[ "Adversarial misspellings are a real-world problem" ]
5,907
qasper
b64c9f2d-d9c2-44b0-b5fc-da77da2a9f87
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how small of a dataset did they train on?\n\nIntroduction\nRecently, deep neural network has been widely employed in various recognition tasks. Increasing the depth of neural network is a effective way to improve the performance, and ...
[ "23085 hours of data" ]
5,554
qasper
bbd44189-539d-4060-8eee-8468b9615176
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they experiment with offering multiple candidate corrections and voting on the model output, since this seems highly likely to outperform a one-best correction?\n\nIntroduction\nDespite the rapid progress of deep learning technique...
[ "No" ]
5,922
qasper
c0cf88e6-f8ad-489a-b1a0-2e31ee7da5df
[{"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...
[ "M-Bert had 76.6 F1 macro score." ]
4,998
qasper
c9199112-ed6a-49f2-9fd5-494be2ec0a8a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what crowdsourcing platform was used?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people ...
[ "Amazon Mechanical Turk" ]
5,794
qasper
cb7b8326-8831-4b43-973c-9f4e4edc5b9e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does RoBERTa outperform BERT?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple use-cases, like systems that deter...
[ "No" ]
3,290
qasper
dc9efdd4-5b48-4b7a-ab62-ddc808aee464
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for evaluation?\n\nIntroduction\nIn the kitchen, we increasingly rely on instructions from cooking websites: recipes. A cook with a predilection for Asian cuisine may wish to prepare chicken curry, but may not kn...
[ "Byte-Pair Encoding perplexity (BPE PPL),\nBLEU-1,\nBLEU-4,\nROUGE-L,\npercentage of distinct unigram (D-1),\npercentage of distinct bigrams(D-2),\nuser matching accuracy(UMA),\nMean Reciprocal Rank(MRR)\nPairwise preference over baseline(PP)" ]
3,949
qasper
dfb69577-bb96-47d7-8f2f-65ebc170cd8b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the sources of the datasets?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribut...
[ "Friends TV sitcom, Facebook messenger chats" ]
4,512
qasper
efca5f44-fda0-4da7-849d-0949751e14d0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which information about typography is included in the corpus?\n\nIntroduction\nSimplified language is a variety of standard language characterized by reduced lexical and syntactic complexity, the addition of explanations for difficult...
[ "font type and font style (e.g., italics, bold print) of a token and its position on the physical page (for PDFs only) was specified as attributes to the token elements of the tokens layer, A separate fonts layer was introduced to preserve detailed information on the font configurations referenced in the tokens lay...
3,693
qasper
f50e908d-eff2-46fd-8b10-46f94066099e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the source of the news sentences?\n\nIntroduction\nNamed entity recognition is an important task of natural language processing, featuring in many popular text processing toolkits. This area of natural language processing has ...
[ "links between Wikipedia articles to generate sequences of named-entity annotated tokens" ]
4,130
qasper
0734b92d-44b0-4e25-8bb4-b5f7d746864a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they train their models on?\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>milk</e1> into the <e2...
[ "relation classification dataset of the SemEval 2010 task 8" ]
3,318
qasper
0d220bfe-8184-4f1d-9b87-b97e98e19f88
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many participants were trying this 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 autocomplet...
[ "100 crowdworkers " ]
2,584
qasper
10b6d8bf-d584-4a67-a2a0-0d4e95feeb12
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what NMT models did they compare with?\n\nIntroduction\nAncient Chinese is the writing language in ancient China. It is a treasure of Chinese culture which brings together the wisdom and ideas of the Chinese nation and chronicles the ...
[ "RNN-based NMT model, Transformer-NMT" ]
5,114
qasper
27441425-6162-4a4e-b416-18f972c50bcf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What cyberbulling topics did they address?\n\nIntroduction\nCyberbullying has been defined by the National Crime Prevention Council as the use of the Internet, cell phones or other devices to send or post text or images intended to hu...
[ "racism, sexism, personal attack, not specifically about any single topic" ]
4,318
qasper
2dac51f2-ed17-4d2e-aa3a-c3d56f463cce
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is trajectory with how rewards extracted?\n\nIntroduction\nText-based games became popular in the mid 80s with the game series Zork BIBREF1 resulting in many different text-based games being produced and published BIBREF2. These g...
[ "explores the state space through keeping track of previously visited states by maintaining an archive" ]
6,936
qasper
3152f9c7-09f5-4542-a5cc-7bd38cf493fa
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the language pairs explored in this paper?\n\nIntroduction\nNeural machine translation (NMT) emerged in the last few years as a very successful paradigm BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . While NMT is generally more flue...
[ "De-En, Ja-En, Ro-En" ]
2,303
qasper
3203a14c-1f10-48c3-bc7f-acf6db95c2db
[{"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...
[ "INLINEFORM2 is queried for the “most informative” instance(s) INLINEFORM3" ]
2,240
qasper
3b4db64b-a48d-4128-9a43-613d4af64a40
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What details are given about the movie domain dataset?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by r...
[ "The number of reviews in this movie corpus is 20,244 and the average number of words in reviews is 39. Each of these reviews has a star-rating score which is indicative of sentiment." ]
5,006
qasper
4281746e-45df-47f2-b655-1f4b4aedf813
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a normal reading paradigm?\n\nIntroduction\nHow humans process language has become increasingly relevant in natural language processing since physiological data during language understanding is more accessible and recorded wit...
[ "read the sentences normally without any special instructions" ]
4,710
qasper
4ac8438b-324e-4fd1-ab61-43c02451ceb3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was their character error rate?\n\nIntroduction\nRecently, deep neural network has been widely employed in various recognition tasks. Increasing the depth of neural network is a effective way to improve the performance, and convo...
[ "Their best model achieved a 2.49% Character Error Rate." ]
5,551
qasper
6942b0f0-31b1-4ee9-abc5-70e47540879c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the results from these proposed strategies?\n\nIntroduction and Background\nMany reinforcement learning algorithms are designed for relatively small discrete or continuous action spaces and so have trouble scaling. Text-adven...
[ "Reward of 11.8 for the A2C-chained model, 41.8 for the KG-A2C-chained model, 40 for A2C-Explore and 44 for KG-A2C-Explore." ]
3,185
qasper
711e7eba-83ec-4ccc-b64f-9081cc1efe7b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the StackExchange dataset collected?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level mea...
[ "Unanswerable" ]
6,246
qasper
849b81b2-af63-46cb-9b2a-ffca2445ff93
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline method is used?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by reviewers on a topic or an...
[ "use the word2vec algorithm, create several unsupervised hand-crafted features, generate document vectors and feed them as input into the support vector machines (SVM) approach" ]
5,002
qasper
85a9db3a-9a89-471e-8c4d-68740206154a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used?\n\nIntroduction\nAutomatically generating text to describe the content of images, also known as image captioning, is a multimodal task of considerable interest in both the computer vision and the NLP communiti...
[ "Existential (OneShape, MultiShapes), Spacial (TwoShapes, Multishapes), Quantification (Count, Ratio) datasets are generated from ShapeWorldICE" ]
4,577
qasper
8b1c7018-2218-48a8-909d-5be232acf106
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What current state of the art method was used for comparison?\n\nIntroduction\nA hashtag is a keyphrase represented as a sequence of alphanumeric characters plus underscore, preceded by the # symbol. Hashtags play a central role in on...
[ "current state-of-the-art approach BIBREF14 , BIBREF15" ]
5,418
qasper
8e35393c-4b43-461a-8f62-37a33750bcc4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what aspects of conversation flow do they look at?\n\nIntroduction\nPublic debates are a common platform for presenting and juxtaposing diverging viewpoints As opposed to monologues where speakers are limited to expressing their own b...
[ "The time devoted to self-coverage, opponent-coverage, and the number of adopted discussion points." ]
3,176
qasper
9060d4df-4535-4dd9-ac32-4bc5789c12c2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages are similar to each other?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known ...
[ "The Nguni languages are similar to each other, The same is true of the Sotho languages" ]
2,610
qasper
a5e8ce12-20f0-4bf2-9f56-1f869b6a3ec5
[{"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...
[ "Avg. GloVe embeddings, Avg. fast-text embeddings, Avg. BERT embeddings, BERT CLS-vector, InferSent - GloVe and Universal Sentence Encoder." ]
5,616
qasper
ae652e75-c292-49d5-b510-2a76dc3f172b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What examples of the difficulties presented by the context-dependent nature of online aggression do they authors give?\n\nIntroduction\nAbusive language refers to any type of insult, vulgarity, or profanity that debases the target; it...
[ "detecting abusive language extremely laborious, it is difficult to build a large and reliable dataset" ]
2,930
qasper
cfd1d543-1a0d-4c4d-9e70-05cd5a5def24
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction and Background\nMany reinforcement learning algorithms are designed for relatively small discrete or continuous action spaces and so have trouble scaling. Text-adventure games—or interaction fic...
[ "a score of 40" ]
3,182
qasper
d29f5514-8a27-4c1c-9aa9-156633416ba4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they incoprorate WordNet into the model?\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 wo...
[ "construct context-gloss pairs from glosses of all possible senses (in WordNet) of the target word" ]
3,006
qasper
de9fe0cd-ded8-4c9c-b870-3686cabf70db
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what debates dataset was used?\n\nIntroduction\nPublic debates are a common platform for presenting and juxtaposing diverging viewpoints As opposed to monologues where speakers are limited to expressing their own beliefs, debates allo...
[ "“Intelligence Squared Debates” (IQ2 for short)" ]
3,172
qasper
e4863b0f-2db2-4a3a-86e7-645f725c463d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is WordNet useful for taxonomic reasoning for this task?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly provided), requires bring...
[ "Yes" ]
9,204
qasper
e68484f2-c2b6-4fd9-8de5-87ceb04214b6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of bioScope corpus?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple use-cases, like systems tha...
[ "Unanswerable" ]
3,290
qasper
ec630594-17f3-41f8-a150-93fb7e155814
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used?\n\nIntroduction\nWith the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter) and news media sites (e.g. Google news) have become important sources of real-world...
[ "FSD dataset, Twitter dataset, Google dataset" ]
5,492
qasper
f125c812-87cf-4472-86c4-3f32827767f4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Up to how many samples do they experiment with?\n\nIntroduction\nDeep neural networks (DNNs), in particular convolutional and recurrent neural networks, with huge architectures have been proven successful in wide range of tasks includ...
[ "we considered 4 different proportions i.e., INLINEFORM0 , INLINEFORM1 , INLINEFORM2 and INLINEFORM3 of the training data to train the classifier" ]
4,146
qasper
f33ddafc-69d7-41ad-8d6e-5c756f9729d0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What hyperparameters are explored?\n\nIntroduction\nThere have been many implementations of the word2vec model in either of the two architectures it provides: continuous skipgram and CBoW (BIBREF0). Similar distributed models of word ...
[ "Dimension size, window size, architecture, algorithm, epochs, hidden dimension size, learning rate, loss function, optimizer algorithm." ]
3,342
qasper
f7a225a1-aff7-4a11-bfa8-3bcf2371cb3b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the previous state of the art?\n\nIntroduction\nModern Standard Arabic (MSA) and Classical Arabic (CA) have two types of vowels, namely long vowels, which are explicitly written, and short vowels, aka diacritics, which are ty...
[ "Farasa BIBREF31, MADAMIRA BIBREF29, RDI (Rashwan et al., 2015), MIT (Belinkow and Glass, 2015), Microsoft ATKS BIBREF28" ]
7,074
qasper
03562983-7540-47af-9538-a1cbe395ca4a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the architecture of their model?\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 automatic sp...
[ "follow the architecture in berard2018end, but have 3 decoder layers like that in pino2019harnessing" ]
3,598
qasper
09e54e0f-1935-4a95-8510-37e16b26e5b3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they measure style transfer success?\n\nIntroduction\nSequence-to-sequence (seq2seq) transformations have recently proven to be a successful framework for several natural language processing tasks, like: machine translation (MT...
[ "Unanswerable" ]
6,335
qasper
1015a03d-dbf9-4ba8-ad25-176b9171a172
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What classifiers have been trained?\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 listens and unders...
[ "KNN\nRF\nSVM\nMLP" ]
2,202
qasper
141158ac-834e-4512-8ca9-d7bc779322cd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What in-domain text did they use?\n\nIntroduction\nPretrained Language Models (PTLMs) such as BERT BIBREF1 have spearheaded advances on many NLP tasks. Usually, PTLMs are pretrained on unlabeled general-domain and/or mixed-domain text...
[ "PubMed+PMC" ]
5,062
qasper
2736f07b-fa37-4d58-9a00-6cdf3cf674d5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What clustering algorithms were used?\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 process e...
[ "CLUTO, Carrot2 Lingo" ]
4,193
qasper
2c15c4f1-1956-4e22-8fd1-3040bb11f79a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset was used?\n\nIntroduction\nPropaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. In the Internet era, thanks to the mechanism of sharing in social networks, propaganda campaigns ...
[ " news articles in free-text format" ]
4,227
qasper
31231e0c-bea8-4e8e-b5a2-122b9a6b74f6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What measures are used for evaluation?\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 ...
[ "correct classification rate (CCR)" ]
2,135
qasper
31a3a65d-ef34-48e4-be5e-9cbee5a1d02f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the StackExchange dataset collected?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level mea...
[ "they obtained computer science related topics by looking at titles and user-assigned tags" ]
6,246
qasper
4058528c-e8ef-4885-9057-4fc049337453
[{"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 score result of 0.8099" ]
2,483
qasper
442e5d13-e674-41ab-92ca-d062b8d8cbc9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what language are the tweets?\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 stra...
[ "English" ]
3,084
qasper
744b85cd-53ad-40ad-b2de-2d24d2d759ea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"by how much did the BLEU score improve?\n\nIntroduction\nMachine translation has made remarkable progress, and studies claiming it to reach a human parity are starting to appear BIBREF0. However, when evaluating translations of the wh...
[ "On average 0.64 " ]
5,130
qasper
789fb909-4430-47ac-8432-750f2935188f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper provide any case studies to illustrate how one can use Macaw for CIS research?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the wa...
[ "No" ]
2,282
qasper
7c49de36-6ca1-46fc-96ee-3752b87c91ad
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much is performance improved on NLI?\n\nIntroduction\nThe ability of semantic reasoning is essential for advanced natural language understanding (NLU) systems. Many NLU tasks that take sentence pairs as input, such as natural lang...
[ " improvement on the RTE dataset is significant, i.e., 4% absolute gain over the BERTBase" ]
5,593
qasper
7e4a2f8c-270d-419a-9b90-fc9d963fd00a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what quantitative analysis is done?\n\nIntroduction\nCLIR systems retrieve documents written in a language that is different from search query language BIBREF0 . The primary objective of CLIR is to translate or project a query into th...
[ "Answer with content missing: (Evaluation section) Given that in CLIR the primary goal is to get a better ranked list of documents against a translated query, we only report Mean Average Precision (MAP)." ]
2,858
qasper
7e7c5317-38be-40ed-9dbf-c152ebafd640
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the parallel corpus used to train the model constraints?\n\nIntroduction\nPrepositional Phrase (PP) attachment disambiguation is an important problem in NLP, for it often gives rise to incorrect parse trees . Stati...
[ "1500 sentences" ]
2,956
qasper
849ef485-21da-4d8c-963a-a10bd8877128
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they compare human-level performance to model performance for their dataset?\n\nIntroduction\nProgress in AI has been driven by, among other things, the development of challenging large-scale benchmarks like ImageNet BIBREF0 in com...
[ "No" ]
6,708
qasper