uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
0513ce97-478d-42df-a62e-74dd205662d1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline models are used?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BIBREF0. This is largely due to inabilities of dia...
[ "Kvmemnn, Feed Yourself, Poly-encoder, BERT bi-ranker" ]
7,235
qasper
16d2adb5-5777-4547-ac70-fb6652d0ee20
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the reported agreement for the annotation?\n\nIntroduction\nCancer is one of the leading causes of death in the world, with over 80,000 deaths registered in Canada in 2017 (Canadian Cancer Statistics 2017). A computer-aided sy...
[ "Unanswerable" ]
2,758
qasper
2063e9ae-9bc3-439e-8a9a-97713242690e
[{"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
224e3d5e-7829-4e51-a136-657e0aa4acd2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the user-defined keywords?\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 could connect [4]. These n...
[ "Words that a user wants them to appear in the generated output." ]
3,506
qasper
2c3c12e9-8335-4f01-ba41-deb318627df4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the decoder LSTMs all have the same weights?\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 seve...
[ "No" ]
1,777
qasper
3894b64d-00e2-42a3-b415-3f60c7daf4f7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What off-the-shelf reward learning algorithm from RL for joint data manipulation learning and model training is adapted?\n\nIntroduction\nThe performance of machines often crucially depend on the amount and quality of the data used fo...
[ " reward learning algorithm BIBREF7" ]
6,950
qasper
3b837f03-90b4-4439-9b0a-5eaae67cf038
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages pairs are used in machine translation?\n\nIntroduction\nRecurrent neural networks (RNNs), including gated variants such as the long short-term memory (LSTM) BIBREF0 have become the standard model architecture for deep l...
[ "German–English" ]
4,699
qasper
3eb5dacd-9135-404f-a9bc-b8c595b7ff4a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is the 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 Language Processi...
[ "The corpus comprises 8,275 sentences and 167,739 words in total." ]
3,587
qasper
409fbf06-1589-40b7-975d-f38130ef6322
[{"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...
[ "rther constrain the model on the data structure in order to prevent inaccurate of even contradictory descriptions" ]
7,007
qasper
52cd48eb-0798-480b-9a25-0b95c8a5cb3b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the 12 languages covered?\n\nIntroduction\nThe lack of annotated training and evaluation data for many tasks and domains hinders the development of computational models for the majority of the world's languages BIBREF0, BIBRE...
[ "Chinese Mandarin, Welsh, English, Estonian, Finnish, French, Hebrew, Polish, Russian, Spanish, Kiswahili, Yue Chinese" ]
21,904
qasper
588982ec-b085-4ad3-b7f0-bfe19f9d3f0d
[{"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...
[ "Word-level Memory Neural Networks (MemNNs) proposed in Bordes et al. (2015)" ]
5,343
qasper
7191933e-ec97-4922-a6d1-48c2d4e9c35f
[{"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...
[ "Unanswerable" ]
5,721
qasper
71c03474-7710-46e0-980f-c7f604a0db8e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the definition of offensive language?\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 mos...
[ " Most prior work focuses on a different aspect of offensive language such as abusive language BIBREF0 , BIBREF1 , (cyber-)aggression BIBREF2 , (cyber-)bullying BIBREF3 , BIBREF4 , toxic comments INLINEFORM0 , hate speech BIBREF5 , BIBREF6 , BIBREF7 , BIBREF8 , BIBREF9 , BIBREF10 , and offensive language BIBREF11 ....
3,085
qasper
7dba2edd-5d50-40c2-bfb0-84729075e7dc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What results do they achieve using their proposed approach?\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 clas...
[ "F-1 score on the OntoNotes is 88%, and it is 53% on Wiki (gold)." ]
3,158
qasper
852a54a7-51ec-4136-ba36-9e8fb93acecb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which machine learning models do they explore?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"ORGANIZATION\"...
[ "BiLSTM, BiLSTM-CNN, BiLSTM-CRF, BiLSTM-CNN-CRF" ]
4,287
qasper
89f783ad-17cd-4994-bfc9-2c7c5d8c357e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their best results on the benchmark datasets?\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 (...
[ "In SNLI, our best model achieves the new state-of-the-art accuracy of 87.0%, we can see that our models outperform other models by large margin, achieving the new state of the art., Our models achieve the new state-of-the-art accuracy on SST-2 and competitive accuracy on SST-5" ]
4,503
qasper
a0ea191d-7f49-44ec-b4ea-d9799ed4c421
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What neural network modules are included in NeuronBlocks?\n\nIntroduction\nDeep Neural Networks (DNN) have been widely employed in industry for solving various Natural Language Processing (NLP) tasks, such as text classification, sequ...
[ "Embedding Layer, Neural Network Layers, Loss Function, Metrics" ]
2,357
qasper
aab3b46b-59a4-4ee6-b75a-c284c1b29e4a
[{"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
b181a536-e24f-4675-b54e-99e1913a984b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which datasets did they experiment 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 data, resulti...
[ "Europarl, MultiUN" ]
5,432
qasper
ba1dc6e1-93a9-430d-8fe1-24e39b292b21
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines were used 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 anonymity fo...
[ "LR + Bag-of-words, Tweet2vec, LR + All Features (tweet-level), LR + All Features (chunk-level), FacTweet (tweet-level), Top-$k$ replies, likes, or re-tweets" ]
2,884
qasper
c651d9e9-d628-409c-9257-ebd6c7ed9c8e
[{"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
e79a6c53-687e-42f5-a4b2-81ce46e14f55
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline is used?\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 users on t...
[ "Waseem and Hovy BIBREF5, Davidson et al. BIBREF9, and Waseem et al. BIBREF10" ]
5,695
qasper
fbeecee0-e1dc-4533-a67c-29682e4f4556
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they employ their indexing-based method to create a sample of a QA Wikipedia dataset?\n\nIntroduction\nQuestion answering (QA) has been a blooming research field for the last decade. Selection-based QA implies a family of tasks tha...
[ "No" ]
2,612
qasper
ffbd3041-d724-4f1d-8565-41c92594f748
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does this method help in sentiment classification task improvement?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs) derived fr...
[ "No" ]
3,683
qasper
0015838e-54ed-47e5-a302-c572b4b02e73
[{"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 predicts the sequence of phoneme or grapheme at each time based on the previous output and context information with a beam search strategy" ]
3,653
qasper
06ec5a8c-2894-405c-9809-9f4109669930
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What cognitive features are used?\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-language and ...
[ "Readability (RED), Number of Words (LEN), Avg. Fixation Duration (FDUR), Avg. Fixation Count (FC), Avg. Saccade Length (SL), Regression Count (REG), Skip count (SKIP), Count of regressions from second half\nto first half of the sentence (RSF), Largest Regression Position (LREG), Edge density of the saliency gaze...
4,864
qasper
074a5a95-c5d7-42b8-84c0-dd9e9f5287a7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different types of entities exist in the dataset?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"OR...
[ "OurNepali contains 3 different types of entities, ILPRL contains 4 different types of entities" ]
4,290
qasper
08e556ea-eef4-45d3-9aa1-50d44ceb15ba
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are employed for South African languages LID?\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...
[ "DSL 2015, DSL 2017, JW300 parallel corpus , NCHLT text corpora" ]
2,613
qasper
09c61b27-a346-404b-9d0c-1306b7c561b1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What boundary assembling method 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 information...
[ "backward greedy search over each sentence's label sequence to identify word boundaries" ]
2,380
qasper
0dc1a348-f152-4dda-9d34-3974d89e7a21
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the improvement in performance for Estonian in the NER task?\n\nIntroduction\nWord embeddings are representations of words in numerical form, as vectors of typically several hundred dimensions. The vectors are used as an input...
[ "0.05 F1" ]
4,621
qasper
14eac31a-04ed-4536-875b-58cae23f49a8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages do they test on for the under-resourced scenario?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaigns...
[ "English, German" ]
5,752
qasper
20e78771-eea4-4f8c-9262-89603669bc3c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what language pairs are explored?\n\nIntroduction\nAlthough Neural Machine Translation (NMT) has dominated recent research on translation tasks BIBREF0, BIBREF1, BIBREF2, NMT heavily relies on large-scale parallel data, resulting in p...
[ "French-English-Spanish (Fr-En-Es), German-English-French (De-En-Fr) and Romanian-English-German (Ro-En-De), Arabic (Ar), Spanish (Es), and Russian (Ru), and mutual translation between themselves constitutes six zero-shot translation" ]
5,431
qasper
2932358b-a91b-4679-8ef4-5848ffd45b54
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they deal with unknown distribution senses?\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 (riverside...
[ "Bayesian classifier has been modified, removing the bias towards frequent labels in the training data" ]
4,989
qasper
2b416aa4-4ac2-44b1-8d44-a66153c63ce3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What semantic and syntactic tasks are used as probes?\n\nIntroduction\nDense word vectors (or embeddings) are a key component in modern NLP architectures for tasks such as sentiment analysis, parsing, and machine translation. These ve...
[ "SimLex, Rare Word, Google Semantic, Semantic Textual Similarity, Word Content (WC) probing, Google Syntactic analogies, Depth, Top Constituent, part-of-speech (POS) tagging" ]
3,416
qasper
3063a1b1-f2c1-4f75-b7b8-7c21acea260b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In the proposed metric, how is content relevance measured?\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing for several decades. To compare and evaluate the performance of d...
[ "The content relevance between the candidate summary and the human summary is evaluated using information retrieval - using the summaries as search queries and compare the overlaps of the retrieved results. " ]
6,267
qasper
30a20e0a-7d9a-437d-a04b-199e01deec9d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which existing strategies are compared?\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 gen...
[ "CDA, REG" ]
3,223
qasper
34bc132a-4853-4256-af27-d1cf8a2e8d58
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments are used to demonstrate the benefits of this approach?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semant...
[ "Calculate test log-likelihood on the three considered datasets" ]
4,298
qasper
3b69ebc8-a7ba-4e9e-9544-fd77ff3e1f48
[{"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...
[ " the same datasets as BIBREF7" ]
6,183
qasper
3b6f5289-33f5-4efb-99f7-633eee5551d0
[{"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
43ef47e2-59f9-42d3-90ad-e5254625dcee
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What different correlations result when using different variants of ROUGE scores?\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing for several decades. To compare and evalua...
[ "we observe that many variants of Rouge scores do not have high correlations with human pyramid scores" ]
6,269
qasper
4edb9d73-a26c-4060-bdfd-c64e39823fd5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the dataset of hashtags sourced?\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 online communication by ...
[ "1,268 randomly selected tweets in the Stanford Sentiment Analysis Dataset BIBREF36, all 12,594 unique English hashtags and their associated tweets from the same Stanford dataset" ]
5,414
qasper
62f331b3-b522-4034-b1f9-a511867a5f8f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which datasets did they experiment with?\n\nIntroduction\nPart-of-speech tagging is now a classic task in natural language processing, for which many systems have been developed or adapted for a large variety of languages. Its aim is ...
[ "Universal Dependencies v1.2 treebanks for the following 16 languages: Bulgarian, Croatian, Czech, Danish, English, French, German,\nIndonesian, Italian, Norwegian, Persian, Polish, Portuguese, Slovenian, Spanish, and Swedish" ]
3,760
qasper
66cb76f0-f8c4-43e5-b7e9-1aac7b97e1fd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they use a crowdsourcing platform?\n\nIntroduction\nUnderstanding what a question is asking is one of the first steps that humans use to work towards an answer. In the context of question answering, question classification allows ...
[ "No" ]
8,028
qasper
6cf804a1-0dba-409a-bde7-88b38fde3351
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What subtasks did they participate in?\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 of their curren...
[ "Answer with content missing: (Subscript 1: \"We did not participate in subtask 5 (E-c)\") Authors participated in EI-Reg, EI-Oc, V-Reg and V-Oc subtasks." ]
3,100
qasper
7099da5a-0e8b-45c5-9595-87b7da38165c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which types of named entities do they recognize?\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...
[ "PER, LOC, ORG, MISC" ]
5,441
qasper
817318c6-a240-42f5-bc83-c0b4a995f5ce
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the different components of the model trained? Is it trained end-to-end?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applie...
[ "the model can be trained end-to-end" ]
5,696
qasper
8cf2baa8-f399-4e09-b30b-1f950aaa8ef7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation criteria and metrics were used to evaluate the generated text?\n\nIntroduction\nAutomated, or robotic, journalism aims at news generation from structured data sources, either as the final product or as a draft for subs...
[ "BLEU, NIST, METEOR, ROUGE-L, CIDEr" ]
5,972
qasper
9e1de53a-83f3-4d1a-8550-156c94876f0e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they determine fake news tweets?\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.oehmichen11, mmolinas@imperia...
[ "an expert annotator determined if the tweet fell under a specific category" ]
3,928
qasper
a01d1bab-710f-4abd-a7b5-5d45d805ae70
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of subwords do they incorporate in their model?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, ...
[ "simple n-grams (like fastText) and unsupervised morphemes" ]
3,208
qasper
be05757b-7c7c-4545-b701-70f6ec3988fb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many articles are in the dataset?\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 have seen a surge ...
[ "244" ]
2,275
qasper
c2933e34-1ff4-4fdd-a03d-eb076c99f038
[{"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 ...
[ "three hand-crafted polarity scores, which are minimum, mean, and maximum polarity scores" ]
5,008
qasper
ccbf38b2-04d3-4a9f-a0b6-c0fd6b28bbd5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the other algorithms tested?\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 sharing and processing capabiliti...
[ "As the simplest baseline, a sensitive data recogniser and classifier, Conditional Random Fields (CRF), spaCy " ]
6,150
qasper
dc0220f3-7db9-4648-8944-2e2dcfb5bc1b
[{"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...
[ "generated with the various combinations of INLINEFORM4 person INLINEFORM5 and INLINEFORM6 emotion word INLINEFORM7 values across the eleven templates, differ only in one word corresponding to gender or race" ]
6,032
qasper
077e5942-3c61-4acd-aa66-9a75685f34f0
[{"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 ...
[ "1000 hours data" ]
5,554
qasper
0fcbd84a-8e63-42e6-85ac-1138a0fb86bc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What discourse relations does it work best/worst for?\n\nIntroduction\nPDTB-style discourse relations, mostly defined between two adjacent text spans (i.e., discourse units, either clauses or sentences), specify how two discourse unit...
[ "explicit discourse relations" ]
5,574
qasper
16300ab3-7af8-4712-8976-d2015227847b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nSpeech-to-Text translation (ST) is essential for a wide range of scenarios: for example in emergency calls, where agents have to respond emergent requests in a foreign language BIBREF0; or in o...
[ "Vanilla ST baseline, Pre-training baselines, Multi-task baselines, Many-to-many+pre-training, Triangle+pre-train" ]
7,491
qasper
1beb2cbf-a61e-45fc-a1fc-a6b64680b0eb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors report results only on English data?\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing for several decades. To compare and evaluate the performance of differen...
[ "Yes" ]
6,266
qasper
34bd3628-9382-41a6-9a95-59b0911bd062
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used to establish that this makes chatbots more knowledgeable and better at learning and conversation? \n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural lan...
[ "Coverage, Avg. MCC and avg. +ve F1 score" ]
8,591
qasper
46550249-41f9-48cd-a47f-aa7bb9a796d8
[{"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
482124d5-520c-481e-a2b2-0a28d5c48d57
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the CORD-19 dataset?\n\nIntroduction\nCoronavirus disease 2019 (COVID-19) is an infectious disease that has affected more than one million individuals all over the world and caused more than 55,000 deaths, as of April 3 in 202...
[ "contains over 45,000 scholarly articles, including over 33,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses" ]
2,991
qasper
5ada56d3-1849-4741-84e1-cfdae4cef8f6
[{"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
651b2a19-d913-4cbb-800e-592b57e018ea
[{"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....
[ " Fisher Information Ratio" ]
2,235
qasper
67259107-2547-4d0f-8a02-0412dd32888c
[{"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...
[ "we apply several CNN and RNN models presented in Tables TABREF12 and TABREF14 and predict the class with the most votes, In case of a tie, we pick one of the most frequent classes randomly" ]
3,317
qasper
71319a48-b804-4b62-8317-8185d84a867e
[{"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...
[ "Unanswerable" ]
9,204
qasper
85242b72-9f34-463b-9c8a-0b5f14a9c6ae
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What state-of-the-art compression techniques were used in the comparison?\n\nIntroduction\nRecently, contextual-aware language models such as ELMo BIBREF0, GPT BIBREF1, BERT BIBREF2 and XLNet BIBREF3 have shown to greatly outperform t...
[ "NoKD, PKD, BERTBASE teacher model" ]
4,883
qasper
a355044c-dcbc-438a-a6c0-84508891bcd5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used?\n\nIntroduction\nRendering natural language descriptions from structured data is required in a wide variety of commercial applications such as generating descriptions of products, hotels, furniture, etc., from a ...
[ "English WIKIBIO, French WIKIBIO , German WIKIBIO " ]
5,865
qasper
af988a26-0641-4797-a8e0-3783a91d4363
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What news article sources are used?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages for the Eng...
[ " the news external references in Wikipedia" ]
10,237
qasper
c789a6e6-ae73-47dd-8917-724a19dd9400
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data is used in experiments?\n\nIntroduction\nThere have been many advances in machine learning methods which help machines understand human behavior better than ever. One of the most important aspects of human behavior is emotio...
[ " tweet dataset created by Wang et al. , CrowdFlower dataset" ]
3,189
qasper
d00cf470-739d-4d1a-a211-ff8c60932613
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics did look at?\n\nIntroduction\nBack to 42 BC, the philosopher Cicero has raised the issue that although there were many Oratory classes, there were none for Conversational skills BIBREF0 . He highlighted how imp...
[ "precision, recall, F1 and accuracy" ]
17,790
qasper
d191bd11-756b-49fd-904f-8061f3dd0d74
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is MSD prediction?\n\nIntroduction\nThis paper describes our approach and results for Task 2 of the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection BIBREF0 . The task is to generate an inflected word for...
[ "morphosyntactic descriptions (MSD)" ]
3,045
qasper
d3ba995f-1f2e-45e1-b719-5305ec65e8e7
[{"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...
[ "participants were instructed to read the sentences naturally, without any specific task other than comprehension" ]
4,710
qasper
debd9630-227f-4838-a0c7-0592d12cb69e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does an individual model consist of?\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 ...
[ "Bayesian model of garg2012unsupervised as our base monolingual model" ]
5,270
qasper
e2ca6f36-f1ae-420f-b0b6-bb40f1f18e8e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What crowdsourcing platform is used?\n\nIntroduction\nThere has been significant progress on Named Entity Recognition (NER) in recent years using models based on machine learning algorithms BIBREF0 , BIBREF1 , BIBREF2 . As with other ...
[ "They did not use any platform, instead they hired undergraduate students to do the annotation." ]
8,637
qasper
f8600fa2-1930-4710-b768-ce6b870f83a4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is it valid to presume a bad medical wikipedia article should not contain much domain-specific jargon?\n\nIntroduction\nAs observed by a recent article of Nature News BIBREF0 , “Wikipedia is among the most frequently visited websites ...
[ "Unanswerable" ]
6,204
qasper
f9892318-7907-42bc-82c4-60b7bd7de458
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What embeddings are used?\n\nIntroduction\nTo appear in Proceedings of International Workshop on Health Intelligence (W3PHIAI) of the 34th AAAI Conference on Artificial Intelligence, 2020.\nPhysician burnout is a growing concern, esti...
[ " simple lookup table embeddings learned from scratch, using high-performance contextual embeddings, which are ELMo BIBREF11, BERT BIBREF16 and ClinicalBERT BIBREF13" ]
6,487
qasper
12b1519b-5494-430b-a496-aeace61cb3c6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the dataset collected?\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 speech recog...
[ "crowdsourcing" ]
3,596
qasper
1bdce58a-999d-43a1-9027-ac39ca42d0e3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How they extract \"structured answer-relevant relation\"?\n\nIntroduction\nQuestion Generation (QG) is the task of automatically creating questions from a range of inputs, such as natural language text BIBREF0, knowledge base BIBREF1 ...
[ "Using the OpenIE toolbox and applying heuristic rules to select the most relevant relation." ]
5,607
qasper
2280af3f-e80c-4403-958e-d7611f347ded
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines used in the paper?\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 could connect [4]. T...
[ "GloVe vectors trained on Wikipedia Corpus with ensembling, and GloVe vectors trained on Airbnb Data without ensembling" ]
3,509
qasper
2ced62c9-9941-46e1-b3c2-bc34b58175ca
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many labels do the datasets have?\n\nIntroduction\nIn practice, it is often difficult and costly to annotate sufficient training data for diverse application domains on-the-fly. We may have sufficient labeled data in an existing d...
[ "719313" ]
6,775
qasper
2ea40ad5-88fb-411f-9371-159acee22996
[{"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" ]
3,114
qasper
4d0299fe-867b-4840-9cb3-64b48a4d5fe4
[{"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...
[ "CFILT-preorder system" ]
2,977
qasper
51575a28-958f-43bb-816d-4bace044c84c
[{"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" ]
3,172
qasper
5b001a07-b1fb-4930-84ae-8bc0c7a9136f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What conclusions do the authors draw from their finding that the emotional appeal of ISIS and Catholic materials are similar?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Interne...
[ "both corpuses used words that aim to inspire readers while avoiding fear, actual words that lead to these effects are very different in the two contexts, our findings indicate that, using proper methods, automated analysis of large bodies of textual data can provide novel insight insight into extremist propaganda"...
4,682
qasper
61955d8f-0835-4976-9fcf-fb8ab2e173ca
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the approach of previous work?\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...
[ "BIBREF11 that uses a character level n-gram language model, 'shallow' naive Bayes classifiers BIBREF12, BIBREF8, BIBREF13, BIBREF14, SVMs BIBREF15, BIBREF16 used an SVM with character n-gram, parts of speech tag features and some other engineered features, The winning approach for DSL 2015 used an ensemble naive B...
2,610
qasper
6730eaa5-731c-458c-a5b2-6087fc4233d4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset does this approach achieve state of the art results on?\n\nData\nWe build and test our MMT models on the Multi30K dataset BIBREF21 . Each image in Multi30K contains one English (EN) description taken from Flickr30K BIBREF...
[ "the English-German dataset" ]
2,509
qasper
6903da37-5be3-46f5-a28c-e392771ea734
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which shallow approaches did they experiment with?\n\nIntroduction\nThe distribution of textual content is typically very fast and catches user attention for only a short period of time BIBREF0 . For this reason, proper wording of the...
[ "SVM with linear kernel using bag-of-words features" ]
3,079
qasper
69612c72-f5b9-4db0-b202-7dff97f1b2b5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which model architectures do they test their word importance approach on?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural differences, suc...
[ "Transformer, RNN-Search model" ]
5,822
qasper
6b46ace0-29f0-4e24-826a-296a4185bce3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nSpeech-to-Text translation (ST) is essential for a wide range of scenarios: for example in emergency calls, where agents have to respond emergent requests in a foreign language BIBREF0; or in o...
[ "Vanilla ST baseline: The vanilla ST BIBREF9 has only a speech encoder and a decoder. It is trained from scratch on the ST-TED corpus.\n\nPre-training baselines: We conduct three pre-training baseline experiments: 1) encoder pre-training, in which the ST encoder is initialized from an ASR model; 2) decoder pre-trai...
7,491
qasper
6f8b229d-b0c7-402e-9623-e8820721eac3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the backoff strategies work?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the data distribution. Even when the per...
[ "Pass-through passes the possibly misspelled word as is, backoff to neutral word backs off to a word with similar distribution across classes and backoff to background model backs off to a more generic word recognition model trained with larger and less specialized corpus." ]
5,902
qasper
8aba0f09-9221-4292-bb57-120408ec1ac4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who judged the irony accuracy, sentiment preservation and content preservation?\n\nIntroduction\nThe irony is a kind of figurative language, which is widely used on social media BIBREF0 . The irony is defined as a clash between the in...
[ "Irony accuracy is judged only by human ; senriment preservation and content preservation are judged both by human and using automatic metrics (ACC and BLEU)." ]
6,084
qasper
950ba699-5d95-4298-b503-fe62053bf4d4
[{"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...
[ "chunk consists of a sorted sequence of tweets labeled by the label of its corresponding account" ]
2,888
qasper
9822e212-ff5d-459b-ae31-83ebf71946d7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets did they use?\n\nIntroduction\nQuestion classification (QC) deals with question analysis and question labeling based on the expected answer type. The goal of QC is to assign classes accurately to the questions based on e...
[ "3500 questions collected from the internet and books." ]
2,874
qasper
a3ac65a8-392b-4e94-b97b-d02f9eacc613
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is meant by closed test setting?\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 Chinese which is written without exp...
[ "closed test limits all the data for learning should not be beyond the given training set, while open test does not take this limitation" ]
5,082
qasper
aaf1990f-e706-43a9-abc7-9f6c84b64935
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who were the experts used for annotation?\n\nIntroduction\nPrivacy policies are the documents which disclose the ways in which a company gathers, uses, shares and manages a user's data. As legal documents, they function using the prin...
[ "Individuals with legal training" ]
5,279
qasper
ab600808-671c-4a75-892a-acb3a538963b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On what Text-Based Games are experiments performed?\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. T...
[ "CoinCollector , CookingWorld " ]
6,937
qasper
b779540a-4cf6-4d58-8f0d-adbf57e88dab
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What argumentation phenomena encounter in actual data are now accounted for by this work?\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...
[ "Unanswerable" ]
20,062
qasper
d8f5db89-7605-4b20-9c02-3b43d2984c5f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the dataset annotated?\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 platforms ...
[ "intents are annotated manually with guidance from queries collected using a scoping crowdsourcing task" ]
3,154
qasper
e570b6a3-8318-4d84-9cfb-647c68f5fa68
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metric is used for evaluation?\n\nIntroduction\nFollowing developing news stories is imperative to making real-time decisions on important political and public safety matters. Given the abundance of media providers and languages,...
[ "Precision, recall, F1, accuracy" ]
4,221
qasper
eac84a75-a09b-4bd4-98ae-680b2f7322b6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which hyperparameters were varied in the experiments on the four tasks?\n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in particular tasks. Such features are of...
[ "number of clusters, seed value in clustering, selection of word vectors, window size and dimension of embedding" ]
3,565
qasper
ec861a9c-4856-4728-a41e-19d4231b903c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the sizes of both datasets?\n\nIntroduction\nText simplification aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning, which can help children, non-native speakers, and pe...
[ "WikiSmall 89 142 sentence pair and WikiLarge 298 761 sentence pairs. " ]
3,186
qasper