uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
daf84f14-7ca9-4460-bc49-8c302731aec0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the dataset annotated?\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 Spanish lang...
[ "no evidence of depression, depressed mood, disturbed sleep, fatigue or loss of energy" ]
2,798
qasper
efba029e-90d1-445f-a795-fb1b15b823c4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they demonstrate why interdisciplinary insights are important?\n\nIntroduction\nIn June 2015, the operators of the online discussion site Reddit banned several communities under new anti-harassment rules. BIBREF0 used this opportun...
[ "No" ]
10,570
qasper
f3934adb-3da4-4210-b986-2f6ab17545c7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the recent abstractive summarization method in this paper?\n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2...
[ " pointer networks with coverage mechanism (PG-net)BIBREF0" ]
5,017
qasper
f4fdc83b-899c-4f9d-8ffa-43a9d98d113c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much do they improve the efficacy of the attention mechanism?\n\nIntroduction\nThe use of RNNs in the field of Statistical Machine Translation (SMT) has revolutionised the approaches to automated translation. As opposed to trad...
[ "Unanswerable" ]
6,994
qasper
fee37c29-aafa-4041-9fb9-db8343225876
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Can the findings of this paper be generalized to a general-purpose task?\n\nIntroduction\nIt is well known that language has certain structural properties which allows natural language speakers to make “infinite use of finite means\" ...
[ "Yes" ]
2,570
qasper
fee3a0be-74e1-422c-a293-02eab381e5ac
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the real-world civil case 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 w...
[ "100 000 documents" ]
5,480
qasper
0d9d203b-5324-4237-b571-c0418314f285
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors hypothesize that humans' robustness to noise is due to their general knowledge?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant qu...
[ "Yes" ]
5,698
qasper
194d2e4a-d954-4466-8021-859d86001df9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper report the performance of a baseline model on South African languages LID?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipeline...
[ "Yes" ]
2,619
qasper
203fe6ee-4675-42be-95c5-25b1aafce144
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of out-of-domain data?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the requisite domain knowledge...
[ "Unanswerable" ]
5,759
qasper
2e3624ee-863d-4ca0-bb70-f2fc31ee643a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what japanese-vietnamese dataset do they use?\n\nIntroduction\nNeural machine translation (NMT) BIBREF0 , BIBREF1 is widely applied for machine translation (MT) in recent years and focuses on popular language pairs such as English INL...
[ "WIT3's corpus" ]
5,566
qasper
3b3dc43a-d731-4a25-b2ac-d2dd5f7381a0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are extracted?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is the anonymity for the auth...
[ "15 emotion types, sentiment classes, positive and negative, care, harm, fairness, cheating, loyalty, betrayal, authority, subversion, sanctity, and degradation, count of question marks, exclamation marks, consecutive characters and letters, links, hashtags, users' mentions, uppercase ratio, tweet length, words emb...
2,880
qasper
515837da-2d1a-445d-9790-64296cfec5ea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the images from a specific domain?\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...
[ "Yes" ]
4,580
qasper
5c077c5a-99f7-4be9-99ec-2e03c814449b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which hand-crafted features are combined with word2vec?\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 ...
[ "polarity scores, which are minimum, mean, and maximum polarity scores, from each review" ]
5,008
qasper
6313f57e-b887-40c5-97e5-def363d94cea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much improvement is gained from Adversarial Reward Augmented Maximum Likelihood (ARAML)?\n\nIntroduction\nNatural text generation, as a key task in NLP, has been advanced substantially thanks to the flourish of neural models BIBRE...
[ "ARAM has achieved improvement over all baseline methods using reverese perplexity and slef-BLEU metric. The maximum reverse perplexity improvement 936,16 is gained for EMNLP2017 WMT dataset and 48,44 for COCO dataset." ]
5,230
qasper
96035b9d-2b70-4660-9d35-a2e71d3961e5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How larger are the training sets of these versions of ELMo compared to the previous ones?\n\nIntroduction\nWord embeddings are representations of words in numerical form, as vectors of typically several hundred dimensions. The vectors...
[ "up to 1.95 times larger" ]
4,625
qasper
99ce9e45-d16c-403c-bd7a-007dce433feb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where are the hotel reviews from?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data h...
[ "TripAdvisor" ]
4,701
qasper
9e470a16-7bd5-4dc6-9486-96e2efd071fa
[{"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
aa4c0baf-2ced-4211-8faa-d788d824489a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what cases is attention different from alignment?\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-ar...
[ "For certain POS tags, e.g. VERB, PRON." ]
4,378
qasper
ad55146e-f762-4480-bf58-a913250ebfde
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many layers does the UTCNN model have?\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 b...
[ "eight layers" ]
5,899
qasper
bf98e3a3-2958-4df4-9b0d-f1d60518659c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their simple voting scheme work?\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>pu...
[ "Among all the classes predicted by several models, for each test sentence, class with most votes are picked. In case of a tie, one of the most frequent classes are picked randomly." ]
3,317
qasper
c37986ef-07f5-48a3-8956-e8591cdb2bd6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the lexicon the same for all languages?\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 ...
[ "Yes" ]
2,612
qasper
c6873e69-a9b3-4761-b63a-9dee3391a3c5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what ner models were evaluated?\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 been activ...
[ "Stanford NER, spaCy 2.0, recurrent model with a CRF top layer" ]
4,127
qasper
c890bcc5-6b57-4bd7-95c1-ca410a4f779e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What neural models are used to encode the text?\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 cons...
[ "neural bag-of-words (NBOW) model, bidirectional long short-term memory network (LSTM), attention-based encoder" ]
5,216
qasper
d92695da-3426-40a9-9235-90cafab45803
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is this hashtag prediction task an established task, or something new?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low fr...
[ "Hashtag prediction for social media has been addressed earlier" ]
3,482
qasper
dbc194c6-19dc-4bb3-afda-4307a4eec3e4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the existing biases?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interactions among use...
[ "systematic and substantial racial biases, biases from data collection, rules of annotation" ]
5,696
qasper
e5d176ea-030d-4e0c-80b6-905628cbc3b2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset did they use?\n\nIntroduction\nBioASQ is a biomedical document classification, document retrieval, and question answering competition, currently in its seventh year. We provide an overview of our submissions to semantic q...
[ "BioASQ dataset" ]
9,715
qasper
edd46901-81da-4d14-b30d-8693f859e986
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the architecture of the span detector?\n\nBackground\nTeaching machine to read and comprehend a given passage/paragraph and answer its corresponding questions is a challenging task. It is also one of the long-term goals of nat...
[ "Unanswerable" ]
2,440
qasper
f23df518-7d08-4694-a898-783f6f3786ea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method's improvements of F1 w.r.t. baseline BERT tagger for Chinese POS datasets?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gi...
[ " +1.86" ]
5,651
qasper
0bc5bad4-3891-4d9d-8eb4-b3e21d18c669
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the real-world civil case 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 w...
[ " INLINEFORM1 cases" ]
5,480
qasper
1272dd3d-3ee5-45c1-897e-d53b194eceac
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which model do they use for end-to-end speech recognition?\n\nIntroduction\nState-of-the-art automatic speech recognition (ASR) systems BIBREF0 have large model capacities and require significant quantities of training data to general...
[ "RNN" ]
2,237
qasper
14d9dc7b-a1e8-41fe-bdbc-4af68e141d33
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which baselines are used 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 generation as a ...
[ "Pointer-Gen, Pointer-Gen+Pos, Pointer-Gen+Same-FT, Pointer-Gen+Pos-FT, Pointer-Gen+RL-ROUGE, Pointer-Gen+RL-SEN" ]
6,346
qasper
206403ec-b43e-4a31-9f7f-18857752a23a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where do they get their ground truth quality judgments?\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,...
[ "quality class labels assigned by the Wikipedia community, a paper is considered to have been accepted (i.e. is positively labeled) if it matches a paper in the DBLP database or is otherwise accepted by any of the following conferences: ACL, EMNLP, NAACL, EACL, TACL, NIPS, ICML, ICLR, or AAAI" ]
5,709
qasper
3114a314-e955-4925-9e65-27c10efce12e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets did they use for evaluation?\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 docum...
[ "Spoken-SQuAD testing set" ]
3,114
qasper
4a87592b-5be2-43e4-8149-09488628521d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the human judgements assembled?\n\nIntroduction\nThe use of RNNs in the field of Statistical Machine Translation (SMT) has revolutionised the approaches to automated translation. As opposed to traditional shallow SMT models, ...
[ "adequacy, precision and ranking values" ]
6,989
qasper
4b4f3bf2-5252-4a85-a250-9325db5930b7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English datasets?\n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in particular tasks. Such features are often motivated by domain...
[ "Yes" ]
3,561
qasper
4e705013-0e9b-4448-bf5d-27048e924c06
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What topic is covered in the Chinese Facebook data? \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 netwo...
[ "anti-nuclear-power" ]
5,900
qasper
54f58217-cf1a-4d00-ab48-f47c1d2311a2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What word level and character level model baselines are used?\n\nIntroduction\nSingle-relation factoid questions are the most common form of questions found in search query logs and community question answering websites BIBREF1 , BIBR...
[ "None" ]
5,343
qasper
5724f545-4630-4303-b512-99a175871682
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the word level baseline they compare to?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low frequency. Estimating th...
[ "The encoder is essentially the same as tweet2vec, with the input as words instead of characters" ]
3,479
qasper
72feed1b-3403-42b7-a34f-50fa8404de48
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What natural language(s) are the recipes written in?\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,...
[ "English" ]
3,953
qasper
841bc472-3273-4df5-aec7-ff33dd6b7a7a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is Arabic one of the 11 languages in CoVost?\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" ]
3,604
qasper
878e7698-c3f5-448f-900f-87fcdfaf12e5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the baselines?\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 determine ...
[ "varied from Maximum Entropy Classifiers (BIBREF4) to Support Vector Machines (BIBREF5,BIBREF6,BIBREF7,BIBREF8), Recursive Neural Networks (BIBREF9,BIBREF10), Convolutional Neural Networks (BIBREF11) and most recently transfer learning-based architectures like Bidirectional Encoder Representation from Transformers ...
3,287
qasper
92b2026d-d990-4d46-9fc1-29a04b6880f8
[{"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...
[ "an intentional and potentially multicast communication, “the expression of an opinion or an action by individuals or groups deliberately designed to influence the opinions or the actions of other individuals or groups with reference to predetermined ends\"" ]
5,829
qasper
a2d31f03-bab7-4613-b855-189eb1eaff3b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What rouge score do they achieve?\n\nIntroduction\nLanguage model pretraining has advanced the state of the art in many NLP tasks ranging from sentiment analysis, to question answering, natural language inference, named entity recogni...
[ "Best results on unigram:\nCNN/Daily Mail: Rogue F1 43.85\nNYT: Rogue Recall 49.02\nXSum: Rogue F1 38.81" ]
6,515
qasper
ac707114-cece-4313-89bc-fb9552c1e9de
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What modalities are supported by Macaw?\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 t...
[ "text, speech, image, click, etc" ]
2,272
qasper
af46e118-68be-49e6-96b4-c0e0ed8ebaa0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the additive modification to the objective function?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building blocks in the...
[ "The cost function for any one of the words of concept word-groups is modified by the introduction of an additive term to the cost function. . Each embedding vector dimension is first associated with a concept. For a word belonging to any one of the word-groups representing these concepts, the modified cost term fa...
8,084
qasper
b2be8e42-6d52-49f3-b356-e2509d5992a0
[{"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...
[ "KG-A2C, A2C, A2C-chained, A2C-Explore" ]
3,182
qasper
baa7a16d-b6a6-4fd8-8746-33c98f1f36d4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What word embeddings do they test?\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 unique...
[ "Bernoulli embeddings, continuous bag-of-words, Distributed Memory version of Paragraph Vector, Global Vectors, equation embeddings, equation unit embeddings" ]
3,789
qasper
cab89c53-f4f6-4da0-aba3-9e434cf68a4d
[{"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
ce15067f-ae9d-46bb-8ca3-6a141fdf2caa
[{"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 ...
[ "recordings of nurse-initiated telephone conversations for congestive heart failure patients" ]
4,633
qasper
d7041bae-6f5f-4e93-81cb-41ecb5e868b7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they calculate variance from the model outputs?\n\nIntroduction\nState-of-the-art automatic speech recognition (ASR) systems BIBREF0 have large model capacities and require significant quantities of training data to generalize....
[ "reducing the variance of an estimator, EGL method in BIBREF3 is almost the same as Eq. ( EQREF8 ), except the gradient's norm is not squared in BIBREF3" ]
2,235
qasper
e0628723-da0a-4fab-aa92-3d7ec1866b2b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What model is used to encode the images?\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 several rel...
[ "LSTM" ]
1,774
qasper
063569fb-29c9-45c6-9a00-e7a18ca24bb2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What topic is covered in the Chinese Facebook data? \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 netwo...
[ "anti-nuclear-power" ]
5,900
qasper
1abc4250-aa73-4b47-8779-efe247d190b8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use number of votes as an indicator of preference?\n\nIntroduction\nThe polarization of actors' expressed preferences is a fundamental concern for studies of legislatures, court systems, and international politics BIBREF0 , BI...
[ "No" ]
10,902
qasper
1fc01e0e-1f80-49b5-824a-e8d9025eeaac
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is a \"chunk of posts\" defined in this work?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is the a...
[ "sequence of $s$ tweets" ]
2,888
qasper
3d0ea5b6-1486-4ce4-8000-4b901301630a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the datasets used in this paper?\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 harassment becomes very...
[ "Twitter dataset provided by organizers containing harassment and non-harassment tweets" ]
3,867
qasper
3eb91c33-bf1f-444d-a7b3-1609c38fb72c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what english 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. forma...
[ "Answer with content missing: (Data section) Penn Treebank (PTB)" ]
3,609
qasper
3fb7bd3b-b971-4eab-bf34-9b36aca52c7d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they verify generalization ability?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/\nEntity linking (EL), mappi...
[ "by evaluating their model on five different benchmarks" ]
5,744
qasper
495b3fd4-d01e-4de2-87e7-4772a82c53a2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they only use adjacent entity mentions or use more than that in some cases (next to adjacent)?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativec...
[ "More than that in some cases (next to adjacent) " ]
5,756
qasper
4d1a6f51-0526-4d54-b56a-d23d4ccb22ff
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other evaluation metrics are looked at?\n\nIntroduction\nSarcasm is an intensive, indirect and complex construct that is often intended to express contempt or ridicule . Sarcasm, in speech, is multi-modal, involving tone, body-la...
[ "Unanswerable" ]
4,866
qasper
9e866663-f84f-448e-a5f4-bae00a22cdfe
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How id Depechemood trained?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Internet to spread its ideology, radicalize individuals, and recruit them to their cause. In comparison t...
[ "By multiplying crowd-annotated document-emotion matrix with emotion-word matrix. " ]
4,669
qasper
a69014ee-1985-4fb2-9af0-a60e37c441a2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was this data collected?\n\nIntroduction\nNowadays, dialog systems are usually designed for a single domain BIBREF0 . They store data in a well-defined format with a fixed number of attributes for entities that the system can prov...
[ "CrowdFlower" ]
3,237
qasper
ab4148a5-1b39-45f3-8bce-0213c213517d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use other evaluation metrics besides ROUGE?\n\nIntroduction\nAutomatic summarization has enjoyed wide popularity in natural language processing due to its potential for various information access applications. Examples include...
[ "Yes" ]
3,868
qasper
ad434f92-53e4-45f3-b01f-bfde70cdb705
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the languages represented in the DSL datasets? \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 ...
[ "Unanswerable" ]
2,613
qasper
b0aca0e3-1a77-4f14-a9ce-500d55b047f8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what bias evaluation metrics are used?\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 gend...
[ "Unanswerable" ]
3,224
qasper
b7cc5a7a-2eca-489e-a096-1eeb70bb6270
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is diversity measured?\n\nIntroduction\nWhen people shop for books online in e-book stores such as, e.g., the Amazon Kindle store, they enter search terms with the goal to find e-books that meet their preferences. Such e-books hav...
[ "average dissimilarity of all pairs of tags in the list of recommended tags" ]
4,423
qasper
c246db06-6500-4414-acf5-ebb69db77ca1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was their performance on emotion detection?\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...
[ "Answer with content missing: (Table 3) Best author's model B-M average micro f-score is 0.409, 0.459, 0.411 on Affective, Fairy Tales and ISEAR datasets respectively. " ]
4,373
qasper
c6309389-e062-4950-955e-9407aa47a955
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where do they get the recipes from?\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 know...
[ "from Food.com" ]
3,950
qasper
c7c04270-5b0c-414b-81bc-2d6ea1c459bd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the goal of investigating NLP gender bias specifically in the news broadcast domain and Anchor role?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous...
[ "create fair systems" ]
5,387
qasper
c979b1cd-fda7-4212-b413-34ec0c185eaf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the effectiveness of this pipeline approach evaluated?\n\nIntroduction\nThe automatic identification, extraction and representation of the information conveyed in texts is a key task nowadays. In fact, this research topic is in...
[ "proposed ontology, which, in our evaluation procedure, was populated with 3121 events entries from 51 documents." ]
3,008
qasper
cd32a7fd-f16e-4393-8f1a-3b49541a11f6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of repetitive and time-consuming activities does their assistant handle?\n\nIntroduction\nRobotic Process Automation (RPA) is a type of software bots that simulates hand-operated human activities like entering data into a sy...
[ " What kind of topic (or sub-topic) a student has a problem with, At which examination mode (i.e., quiz, chapter level training or exercise, section level training or exercise, or final examination) the student is working right now, the exact question number and exact problem formulation" ]
8,438
qasper
d9b638a8-92cd-4208-832d-d8fe9b4c29a5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they show on which examples how conflict works better than attention?\n\nIntroduction\nModelling the relationship between sequences is extremely significant in most retrieval or classification problems involving two sequences. Trad...
[ "Yes" ]
3,185
qasper
e337d880-d185-473e-b19a-375e65811f1d
[{"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...
[ "ASR" ]
5,381
qasper
ead87bd9-f3bb-400c-ada6-1142e6ea8bf3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are weights dynamically adjusted?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives concrete examples: for the Named Entity Recogniti...
[ "One can think $(1-p_{i1})$ as a weight associated with each example, which changes as training proceeds. The intuition of changing $p_{i1}$ to $(1-p_{i1}) p_{i1}$ is to push down the weight of easy examples. For easy examples whose probability are approaching 0 or 1, $(1-p_{i1}) p_{i1}$ makes the model attach sign...
5,635
qasper
f260c1ec-61a2-4f7c-9635-ed8b85d77b7e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are improvements for these two approaches relative to ELMo-only baselines?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs...
[ " the performance differences across all tasks are small enough " ]
3,689
qasper
0b3060c0-308a-456d-b43f-1e3d287ab6c1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large are the improvements of the Attention-Sum Reader model when using the BookTest dataset?\n\nIntroduction\nSince humans amass more and more generally available data in the form of unstructured text it would be very useful to t...
[ "INLINEFORM2 " ]
5,282
qasper
1439624f-8d2f-4aed-9fca-f43660173986
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines are presented?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data has b...
[ "Logistic regression, LSTM, End-to-end memory networks, Deep projective reader" ]
4,700
qasper
239a2268-e203-4fa4-813d-070cb992d90f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use active learning to create 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 computer vision, and SNLI BIBR...
[ "Yes" ]
6,705
qasper
2a8c2c1f-060a-4043-b790-1cd420ed7616
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their NER model learn NER from both text and images?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opinions and preferences of groups and individuals. These ins...
[ "Yes" ]
5,446
qasper
2d56ee52-8cbe-4548-acc3-c470b6cf87eb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is their ROUGE score?\n\nIntroduction\nAutomatic summarization has enjoyed wide popularity in natural language processing due to its potential for various information access applications. Examples include tools which aid users na...
[ "Unanswerable" ]
3,865
qasper
3be392d2-a570-44f8-9b2b-5101a85451e2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was their highest MRR score?\n\nIntroduction\nBioASQ is a biomedical document classification, document retrieval, and question answering competition, currently in its seventh year. We provide an overview of our submissions to sem...
[ "0.5115" ]
9,717
qasper
51745518-3189-4517-b6e0-b21f91c0c0fd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which classification algorithm do they use for s2sL?\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 i...
[ "MLP" ]
4,148
qasper
6610bc6c-9d3a-4091-ad9c-49aee32d2153
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How better is performance compared to previous state-of-the-art models?\n\nIntroduction\nChinese word segmentation (CWS) is a task for Chinese natural language process to delimit word boundary. CWS is a basic and essential task for Ch...
[ "F1 score of 97.5 on MSR and 95.7 on AS" ]
5,087
qasper
7e705ba2-c87c-4193-b2ba-885183f6d4a3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what topics did they label?\n\nIntroduction\nSummarization of patient information is essential to the practice of medicine. Clinicians must synthesize information from diverse data sources to communicate with colleagues and provide co...
[ "Demographics Age, DiagnosisHistory, MedicationHistory, ProcedureHistory, Symptoms/Signs, Vitals/Labs, Procedures/Results, Meds/Treatments, Movement, Other." ]
3,945
qasper
851a8cb5-7a7c-4883-913e-1f41555ca2f5
[{"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...
[ "Unanswerable" ]
3,290
qasper
85e0c28a-9f9d-4e67-abf9-4ec0f7c3f5c0
[{"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 BIBREF12 , Twitter, and Google datasets" ]
5,492
qasper
876c5015-5065-4700-8722-390205c17446
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate only on English datasets?\n\nIntroduction\nData annotation is a major bottleneck for the application of supervised learning approaches to many problems. As a result, unsupervised methods that learn directly from unlab...
[ "Yes" ]
5,843
qasper
90ec7fd2-e076-4d8c-83d2-ea9722b34cc1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method improvements of F1 for paraphrase identification?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives concrete examples: fo...
[ "+0.58" ]
5,641
qasper
9aa7ee98-05d6-44f3-a1ab-57c257b8b459
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\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 whole documents rat...
[ " MT system on the data released by BIBREF11" ]
5,125
qasper
ab0fb803-14a7-413e-bc82-210b1cf82dcc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which approach out of two proposed in the paper performed better in experiments?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Wo...
[ "CJFA encoder" ]
5,212
qasper
bfa54bbb-6da0-474d-87e7-a4b1ee80e99a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors also analyze transformer-based architectures?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/.\nSentenc...
[ "No" ]
5,774
qasper
c282e296-1cc7-4141-a8e9-2339f45cfb31
[{"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...
[ "Level 1, Level 2 and Level 3." ]
2,276
qasper
cb595608-c4c9-440a-a9a0-d7953ba3b286
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What textual patterns are extracted?\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 e...
[ "patterns for generating all types of errors" ]
2,710
qasper
d8da1071-6b70-4339-bb91-150fa0c47b65
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metric do they use?\n\nIntroduction\nThis research addresses the problem of representing the semantics of text documents in multi-lingual comparable corpora. We present a new approach to this problem, based on neural e...
[ "Accuracy" ]
3,437
qasper
e61d46a8-6e7d-416b-838e-5d0a29765593
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who were the human evaluators used?\n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2. However, complex neural summa...
[ "20 evaluators were recruited from our institution and asked to each perform 20 annotations" ]
5,011
qasper
f0b30b04-2421-4a76-9fc4-8b676e0ec4e0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what standard dataset were used?\n\nIntroduction\nInformation extraction tasks have become very important not only in the Web, but also for in-house enterprise settings. One of the crucial steps towards understanding natural language ...
[ "CoNLL2003-testA, GENIA" ]
4,083
qasper
f631164c-0ecf-4a3a-b8df-34ffcb8aab78
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data sources do they use for creating 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 computer vision, and SNLI...
[ "Wikipedia (of 250-600 characters) from the manually curated HotpotQA training set, Manually Annotated Sub-Corpus (MASC) of the Open American National Corpus), RTE5" ]
6,706
qasper
0f791e85-87bb-4a05-8832-7ebc92c8b81a
[{"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...
[ "KG-A2C-chained and KG-A2C-Explore both pass the bottleneck of a score of 40" ]
3,185
qasper
13d30b11-5b66-411d-b755-1159ffd74de7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are used to represent the novelty of news articles to entity pages?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a r...
[ "KL divergence between the language model of INLINEFORM5 and articles in INLINEFORM6" ]
10,245
qasper
209cf045-f53b-4116-bb68-06c3a887be18
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what challenges are identified?\n\nIntroduction\nTypical speech-to-text translation systems pipeline automatic speech recognition (ASR) and machine translation (MT) BIBREF0 . But high-quality ASR requires hundreds of hours of transcri...
[ "Assigning wrong words to a cluster, Splitting words across different clusters, sparse, giving low coverage" ]
2,063
qasper
2d4e5a19-3d0a-426b-afd4-85fa27ad869d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What new fine-tuning methods are presented?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interact...
[ "BERT based fine-tuning, Insert nonlinear layers, Insert Bi-LSTM layer, Insert CNN layer" ]
5,699
qasper