uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
5c10a2b9-0d07-4453-a624-aeaf5d102ce7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is specific to multi-granularity and multi-tasking neural arhiteture design?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social med...
[ "Multi-tasking is addressed by neural sequence tagger based on LSTM-CRF and linguistic features, while multi-granularity is addressed by ensemble of LSTM-CRF and BERT." ]
2,447
qasper
62369717-f40d-4708-bf06-8b016d1561c4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is non-standard pronunciation identified?\n\nIntroduction\nRecent years have seen unprecedented progress for Natural Language Processing (NLP) on almost every NLP subtask. Even though low-resource settings have also been explored,...
[ "Original transcription was labeled with additional labels in [] brackets with nonstandard pronunciation." ]
4,176
qasper
626dffed-71c7-4165-a4a4-5316efb2c648
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset did they use?\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 current customers ...
[ "Spanish tweets were scraped between November 8, 2017 and January 12, 2018, Affect in Tweets Distant Supervision Corpus (DISC)" ]
3,098
qasper
642237e5-5395-4300-b250-2c7ce4b74958
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of social media did they consider?\n\nIntroduction\nExplanations of happenings in one's life, causal explanations, are an important topic of study in social, psychological, economic, and behavioral sciences. For example, ps...
[ "Facebook status update messages" ]
5,201
qasper
661ce48e-de45-4ea6-a582-da48beb81063
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the languages they use in their experiment?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect and annotate d...
[ "English, Spanish, Finnish" ]
5,516
qasper
669b1df4-3cde-4e66-a2c9-6b8fd3daf063
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What did the best systems use for their model?\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 free.\n[4]https://git...
[ "Unanswerable" ]
2,482
qasper
73936f45-9f5c-41d1-b6da-d56eda9ab6b0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\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 INLINEFORM0 French, Englis...
[ "traditional phrase-based statistical machine translation (SMT), NMT system" ]
5,561
qasper
8f30e40f-0d65-4cdc-a1a2-81633dbc1b9e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does the \"sensitivity\" quantity denote?\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 w...
[ "the number of distinct word recognition outputs that an attacker can induce" ]
5,904
qasper
98c1dcbf-e5cf-4dc2-b87a-fe0215a45f96
[{"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...
[ "(VVD shop_VV0 II, VVD shopping_VVG II)" ]
2,710
qasper
a2c0ac54-9ca0-4585-80e6-2a05ac98d495
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the state-of-the-art system?\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 onl...
[ "doc2vec , CNN, DAN, Tree-LSTM, DRNN, LSTMN, C-LSTM, SPGK, WMD, S-WMD, Semantic-CNN, LSTM-GRNN, HN-ATT" ]
6,276
qasper
a77424db-eeb7-4987-9abd-596c5408ff00
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is imbalance in analyzed corpora?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous studies have been conducted in order to evaluate the presence of w...
[ "Women represent 33.16% of the speakers" ]
5,376
qasper
c26d8ca0-2721-406a-8c1a-63af935fcce0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which non-english language had the best performance?\n\nIntroduction\nWith the steady growth in the commercial websites and social media venues, the access to users' reviews have become easier. As the amount of data that can be mined ...
[ "Russian" ]
3,544
qasper
c3babf51-5baf-457f-a31e-d3363ffae720
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is diversity measured?\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 communi...
[ "diversity score as the ratio of observed number versus optimal number" ]
4,577
qasper
c8b9d841-570f-401d-a5d2-4f5db71212b2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines used?\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 autocomplete system would be able to infe...
[ "Unif and Stopword" ]
2,582
qasper
de2f7e77-42ef-472d-8315-59c0aae7baea
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many documents are in the new corpus?\n\nIntroduction\nThe automatic processing of medical texts and documents plays an increasingly important role in the recent development of the digital health area. To enable dedicated Natural ...
[ "53 documents" ]
3,590
qasper
ea39ff5e-0713-476c-ad55-b27f96e42ca5
[{"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...
[ "In pass-through, the recognizer passes on the possibly misspelled word, 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
f353bd21-fca6-44df-ab13-3e6b118102b0
[{"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
f6392105-f64c-454a-a4e6-3e6a07f55f88
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many total combined features were there?\n\nIntroduction\nTwitter, a micro-blogging and social networking site has emerged as a platform where people express themselves and react to events in real-time. It is estimated that nearly...
[ "Fourteen " ]
2,366
qasper
f7ce2f72-3cb5-46c5-acfc-ba45a749910d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are their results on both datasets?\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 a...
[ "Combining pattern based and Machine translation approaches gave the best overall F0.5 scores. It was 49.11 for FCE dataset , 21.87 for the first annotation of CoNLL-14, and 30.13 for the second annotation of CoNLL-14. " ]
2,712
qasper
0237538c-2c01-4b97-aead-e7ae41fdc23f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of inflections are considered?\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 i...
[ "Unanswerable" ]
3,048
qasper
0cfca8ee-f183-45d8-8246-d8d77d92a653
[{"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" ]
3,079
qasper
25a57adc-a92e-41a1-9e5a-c565fb8149df
[{"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...
[ "baseline without knowledge distillation (termed NoKD), Patient Knowledge Distillation (PKD)" ]
4,883
qasper
2aa6d73b-bb3e-486c-a122-cd536d4fd3af
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which component has the greatest impact on performance?\n\nIntroduction\nThe concept of message passing over graphs has been around for many years BIBREF0, BIBREF1, as well as that of graph neural networks (GNNs) BIBREF2, BIBREF3. How...
[ "Increasing number of message passing iterations showed consistent improvement in performance - around 1 point improvement compared between 1 and 4 iterations" ]
6,276
qasper
31bd428a-1482-4453-a06e-de3bc8d6b11f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the threshold for determining that a tweet has gone viral?\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.oeh...
[ "1000" ]
3,933
qasper
370399d9-3327-474c-9df9-28637e7da51e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many users do they look at?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friends are, what t...
[ "20,000" ]
5,298
qasper
45dbebe6-c9ae-4665-aff7-3ad8f78a8017
[{"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...
[ "On high level, we indirectly evaluate the content relevance between the candidate summary and the human summary using information retrieval." ]
6,267
qasper
4f29fa00-edab-4d98-9394-7c4f7bc19238
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"For which languages do they build word embeddings for?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, and ...
[ "English" ]
3,206
qasper
554163df-f997-44ca-850b-b102ed85159a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what accents are present in the corpus?\n\nIntroduction\nNowadays deep learning techniques outperform the other conventional methods in most of the speech-related tasks. Training robust deep neural networks for each task depends on th...
[ "Unanswerable" ]
5,099
qasper
58eafcbd-c752-427c-91c4-b1490b2565c8
[{"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
5e61e8ba-c6a4-4eb4-9294-6ce638dc5c8f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics are used?\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 article title ma...
[ "accuracy" ]
3,077
qasper
684eb365-d6a6-4628-9cec-eb2d3539ec70
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What labels for antisocial events are available in datasets?\n\nIntroduction\n“Ché saetta previsa vien più lenta.”\n– Dante Alighieri, Divina Commedia, Paradiso\nAntisocial behavior is a persistent problem plaguing online conversation...
[ "The Conversations Gone Awry dataset is labelled as either containing a personal attack from withint (i.e. hostile behavior by one user in the conversation directed towards another) or remaining civil throughout. The Reddit Change My View dataset is labelled with whether or not a coversation eventually had a commen...
6,586
qasper
87f30218-62eb-4bde-9ca4-fd0a23e995b0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is jiant compatible with models in any programming language?\n\nIntroduction\nThis paper introduces jiant, an open source toolkit that allows researchers to quickly experiment on a wide array of NLU tasks, using state-of-the-art NLP m...
[ "Yes" ]
3,368
qasper
8a4eecc1-ae96-4352-9d25-87e22d708835
[{"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...
[ "0.6103" ]
9,717
qasper
9c7f4cdc-8cee-4e9c-9b6c-bb6d31082da9
[{"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)" ]
5,017
qasper
9f83a935-2b98-4d65-bf2d-bfef2586ed4b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are two datasets model is applied to?\n\nIntroduction\n“Ché saetta previsa vien più lenta.”\n– Dante Alighieri, Divina Commedia, Paradiso\nAntisocial behavior is a persistent problem plaguing online conversation platforms; it is ...
[ "An expanded version of the existing 'Conversations Gone Awry' dataset and the ChangeMyView dataset, a subreddit whose only annotation is whether the conversation required action by the Reddit moderators. " ]
6,584
qasper
ab450697-0852-4a3a-8c2a-542b88984c6a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\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 INLINEFORM0 French, Englis...
[ "traditional phrase-based statistical machine translation (SMT), NMT system" ]
5,561
qasper
ad303e32-b648-4000-837f-8effef5b0e6e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which parallel corpora are used?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question answering, and other NLP...
[ "English (EN) and German (DE) sections of the CoNLL 2009 corpus BIBREF13, EN-DE section of the Europarl corpus BIBREF14" ]
5,269
qasper
b30b7cba-aef8-4a27-b1aa-dce8ea35de6b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics are looked at for classification tasks?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their w...
[ "Precision, Recall and F-measure" ]
4,197
qasper
b6c6b9d4-2d45-4d13-870e-6344809f8cd2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages are part of the corpus?\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 spe...
[ "French (Fr), German (De), Dutch (Nl), Russian (Ru), Spanish (Es), Italian (It), Turkish (Tr), Persian (Fa), Swedish (Sv), Mongolian (Mn) and Chinese (Zh)" ]
3,598
qasper
bc744507-0002-4c8c-8eaf-3ca02a4bf998
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the LSTM baseline a sub-word model?\n\nIntroduction\nLanguage modeling is a probabilistic description of language phenomenon. It provides essential context to distinguish words which sound similar and therefore has one of the most ...
[ "Yes" ]
2,735
qasper
cc6027e2-8f7b-42ba-993d-e0be20bdb615
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where does the ancient Chinese dataset come from?\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 chro...
[ "ancient Chinese history records in several dynasties (about 1000BC-200BC) and articles written by celebrities of that era" ]
5,114
qasper
e4394631-76ae-4017-88de-e1805237447f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were crowd workers instructed to identify important elements in large document collections?\n\nIntroduction\nMulti-document summarization (MDS), the transformation of a set of documents into a short text containing their most impo...
[ "They break down the task of importance annotation to the level of single propositions and obtain a score for each proposition indicating its importance in a document cluster, such that a ranking according to the score would reveal what is most important and should be included in a summary." ]
5,680
qasper
e985377c-55c9-455a-a594-8c1b5db00621
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which models/frameworks do they compare to?\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 including ...
[ "Eusboost, MWMOTE" ]
4,145
qasper
ec747626-4442-4a9c-9651-e75ef11f8a5a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the professional translation or the machine translation introduce the artifacts?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibi...
[ "Yes" ]
5,518
qasper
ec85ec74-1fd5-4808-b561-101dfd95b7b1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of 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\", \"ORGANIZATION\" and othersBIB...
[ "ILPRL contains 548 sentences, OurNepali contains 3606 sentences" ]
4,287
qasper
ee822648-6b93-4ece-b7e8-2bec2a128374
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is order of \"words\" important in car speak language?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer...
[ "Unanswerable" ]
2,208
qasper
f9002f7b-6826-483d-80c5-b5dd56c8f410
[{"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...
[ "Unanswerable" ]
5,843
qasper
10666170-4b40-4147-8b50-8a19dfa344ed
[{"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...
[ "low coverage of audio, difficulty in cross-speaker clustering" ]
2,063
qasper
14b2aaa3-5404-4fc0-bee0-0ee936748d46
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many total combined features were there?\n\nIntroduction\nTwitter, a micro-blogging and social networking site has emerged as a platform where people express themselves and react to events in real-time. It is estimated that nearly...
[ "Unanswerable" ]
2,366
qasper
1bf3d3d4-7ae5-4dbd-a1b7-34e658767f19
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors mention any downside of lemmatizing input before training ELMo?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems....
[ "Yes" ]
4,031
qasper
20bebd49-54b1-4258-b6ce-4b07061142ca
[{"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...
[ "INLINEFORM0 scores" ]
3,609
qasper
2ac53895-0320-43c3-98f0-2ebd6a9bd39c
[{"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...
[ "BIBREF7" ]
6,950
qasper
2c3509d6-8122-466d-9c3e-e0f78338c965
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they release their data set of academic papers?\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, inc...
[ "Unanswerable" ]
5,709
qasper
449d195f-de22-4739-a82c-aafc2d81110b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\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 common in Twi...
[ " LastStateRNN, AvgRNN, AttentionRNN" ]
3,864
qasper
641d7158-7630-4afe-9d97-03b6dd13cc74
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used?\n\nIntroduction\nThe concept of message passing over graphs has been around for many years BIBREF0, BIBREF1, as well as that of graph neural networks (GNNs) BIBREF2, BIBREF3. However, GNNs have only recently s...
[ "Reuters, BBCSport, Polarity, Subjectivity, MPQA, IMDB, TREC, SST-1, SST-2, Yelp2013" ]
6,272
qasper
69edc2bd-be5e-4523-8ebf-ac2295eeabfd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many tweets are in the dataset?\n\nIntroduction\nDisclaimer: Due to the nature of the paper, some examples contain highly offensive language and hate speech. They don't reflect the views of the authors in any way, and the point of...
[ "10,000" ]
7,104
qasper
7122caba-aa79-46bb-8e4f-2a6156bb1ca4
[{"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...
[ "5 percent points." ]
4,621
qasper
71bd5684-b6bc-4608-a685-e6835e71b554
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the topics pulled from Reddit?\n\nIntroduction\n“I'm supposed to trust the opinion of a MS minion? The people that produced Windows ME, Vista and 8? They don't even understand people, yet they think they can predict the behav...
[ "training data has posts from politics, business, science and other popular topics; the trained model is applied to millions of unannotated posts on all of Reddit" ]
5,756
qasper
8c9dd833-cdcc-43bb-85b5-0d5132fa7ce7
[{"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...
[ "WMT15 German-to-English, RWTH German-English dataset" ]
4,374
qasper
9481ee7c-9881-4308-8160-8b35c540d72c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is the new Nepali NER 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\", \"ORGANIZATION\" and oth...
[ "Dataset contains 3606 total sentences and 79087 total entities." ]
4,290
qasper
962e0c12-a51c-40c0-bf1a-79380864e85b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the limitations of existing Vietnamese word segmentation systems?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural language pr...
[ " ambiguous words, unknown words" ]
4,685
qasper
97553cae-c489-4042-9051-6a0ad9acf2bf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\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 behavio...
[ "Yes" ]
3,191
qasper
a0a2da7d-5f8c-42a0-b68f-61dbce96f617
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What user variations have been tested?\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 autocomplete system would be ab...
[ "completion times and accuracies " ]
2,582
qasper
a4fff85c-904e-4775-bd29-410f81b2e5bc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the previous best model?\n\nIntroduction\nQuestion answering (QA) has drawn a lot of attention in the past few years. QA tasks on images BIBREF0 have been widely studied, but most focused on understanding text documents BIBRE...
[ "Unanswerable" ]
3,113
qasper
a5920d6c-26d2-4167-bbc2-f7c68b5792f8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What machine learning and deep learning methods are used for RQE?\n\nIntroduction\nWith the availability of rich data on users' locations, profiles and search history, personalization has become the leading trend in large-scale inform...
[ "Logistic Regression, neural networks" ]
10,190
qasper
aca79d3e-2a26-4667-9328-0b196485fd4e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they use a crowdsourcing platform for annotations?\n\nIntroduction\nThe focus of the word sense disambiguation (WSD) task is polysemy, i.e. words having several substantially different meanings. Two common examples are bank (river...
[ "No" ]
4,990
qasper
bae49d24-8af0-486a-a49d-9b5e55050a76
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"by how much did their model improve?\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...
[ "For the WikiLarge dataset, the improvement over baseline NMT is 2.11 BLEU, 1.7 FKGL and 1.07 SARI.\nFor the WikiSmall dataset, the improvement over baseline NMT is 8.37 BLEU." ]
3,186
qasper
c2812d03-1ec4-4658-b64b-848fb647ad50
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of stylistic features are obtained?\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-l...
[ "Unanswerable" ]
4,867
qasper
c951ef90-24e2-430d-b8f7-1a3c5a865df6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\n\nIntroduction\nNeural machine translation (NMT) BIBREF0 , BIBREF1 , BIBREF2 has enabled end-to-end training of a translation system without needing to deal with word alignments, translation rules, and complica...
[ "pivot-based translation relying on a helping language BIBREF10, nduction of phrase tables from monolingual data BIBREF14 , attentional RNN-based model (RNMT) BIBREF2, Transformer model BIBREF18, bi-directional model BIBREF11, multi-to-multi (M2M) model BIBREF8, back-translation BIBREF17" ]
6,552
qasper
cee0f5d4-a6f8-4570-a2e5-a881d5a0d0c0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their distribution results?\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@imperial.a...
[ "Distributions of Followers, Friends and URLs are significantly different between the set of tweets containing fake news and those non containing them, but for Favourites, Mentions, Media, Retweets and Hashtags they are not significantly different" ]
3,926
qasper
d98633b4-5c70-4c85-9763-46a6e8c5fd45
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what ml based approaches were compared?\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 question...
[ "Multi-Layer Perceptron (MLP), Naive Bayes Classifier (NBC), Support Vector Machine (SVM), Gradient Boosting Classifier (GBC), Stochastic Gradient Descent (SGD), K Nearest Neighbour (K-NN) and Random Forest (RF)" ]
2,875
qasper
db9cccf6-a250-455d-a0d8-c3ed0424a475
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline?\n\nIntroduction\nThe apparent rise in political incivility has attracted substantial attention from scholars in recent years. These studies have largely focused on the extent to which politicians and elected off...
[ "Unanswerable" ]
4,408
qasper
dcdd08eb-af65-45e6-ab58-9a2e15d43dd7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is segmentation quality evaluated?\n\nIntroduction\nRhetorical Structure Theory (RST) BIBREF0 is a technique of Natural Language Processing (NLP), in which a document can be structured hierarchically according to its discourse. Th...
[ "Segmentation quality is evaluated by calculating the precision, recall, and F-score of the automatic segmentations in comparison to the segmentations made by expert annotators from the ANNODIS subcorpus." ]
5,220
qasper
fe16ac5b-14b4-46e6-af15-53cbfa0b12c0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what algorithms did they use?\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 ...
[ "popularity-based, similarity-based, hybrid" ]
4,424
qasper
09c83593-24b0-4e50-84ae-c29eb49bba60
[{"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
0e82623a-ad1e-497f-bb96-9b8688a7103a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset statistics are provided?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people ...
[ "More than 2,100 texts were paired with 15 questions each, resulting in a total number of approx. 32,000 annotated questions. 13% of the questions are not answerable. Out of the answerable questions, 10,160 could be answered from the text directly (text-based) and 3,914 questions required the use of commonsense kn...
5,793
qasper
111dfb67-9f42-43bc-8f05-c88cbf887982
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which SVM approach resulted in the best performance?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP)...
[ "Target-1" ]
2,823
qasper
11fc5875-8339-4983-8adc-0a53aad79ecb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baseline methods?\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 domain (...
[ "(1) Naive, (2) mSDA BIBREF7, (3) NaiveNN, (4) AuxNN BIBREF4, (5) ADAN BIBREF16, (6) MMD" ]
6,773
qasper
1210eeca-ad23-428f-b922-892fdc4597fa
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is the Twitter dataset?\n\nIntroduction\nRecently, people have started looking at online forums either as a primary or secondary source of counseling services BIBREF0. BIBREF1 reported that over the first five years of opera...
[ "1,873 Twitter conversation threads, roughly 14k tweets" ]
4,713
qasper
1450dbcc-7d28-449e-8a8d-0162ad422260
[{"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, Waseem et al. BIBREF10" ]
5,695
qasper
20f8a55d-4f7d-4222-81fa-3f537365f8b6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What traditional linguistics features did they use?\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, ...
[ "Unanswerable" ]
4,867
qasper
24bef8aa-8bf4-416d-81c5-aadad6977d2f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does a node in the network approach repesent?\n\nIntroduction\nThe polarization of actors' expressed preferences is a fundamental concern for studies of legislatures, court systems, and international politics BIBREF0 , BIBREF1 , ...
[ "Unanswerable" ]
10,902
qasper
25c8f8e3-fb02-4e88-be85-e21f9203fcd9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"did they use a crowdsourcing platform for manual annotations?\n\nIntroduction\nNamed entity recognition is an important task of natural language processing, featuring in many popular text processing toolkits. This area of natural lang...
[ "No" ]
4,132
qasper
3e989903-d026-46e8-998c-4ba92866695c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which deep learning architecture do they use for sentence segmentation?\n\nIntroduction\nAutomatic summarization, machine translation, question answering, and semantic parsing operations are useful for processing, analyzing, and extra...
[ "Bi-LSTM-CRF" ]
9,317
qasper
8d97af06-8c6c-44ff-8e70-40cd7e4c0bc7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What topics are included in the debate 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 networks have...
[ "abortion, gay rights, Obama, marijuana" ]
5,898
qasper
951596e1-fd63-4725-bf35-f85b199d0e29
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which methods are considered to find examples of biases and unwarranted inferences??\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to tr...
[ "spot patterns by just looking at a collection of images, tag all descriptions with part-of-speech information, I applied Louvain clustering" ]
2,935
qasper
a5de1c41-ba2a-4794-9bce-38fc75ea7d03
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English?\n\nIntroduction\nDeep Neural Networks (DNN) have been widely employed in industry for solving various Natural Language Processing (NLP) tasks, such as text classification, sequence labeling, que...
[ "Yes" ]
2,354
qasper
af821cc6-5ee0-4067-a697-1d795e295aa1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English datasets?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions. Since the answer to each question is ...
[ "Yes" ]
5,688
qasper
b0e05f5c-9446-49ba-b74c-c35a285c3ce9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are meaningful chains in the graph selected?\n\nIntroduction\nKnowledge graphs BIBREF0 enable structured access to world knowledge and form a key component of several applications like search engines, question answering systems an...
[ "No" ]
6,212
qasper
b4d0123d-8e0e-4ab5-b62f-6c77f0ad7451
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is their definition of tweets going viral?\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@...
[ "Viral tweets are the ones that are retweeted more than 1000 times" ]
3,929
qasper
b7ac1435-54a7-483a-a183-f9ea1c133e9c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset has been used in this work?\n\nIntroduction\nText classification has become an indispensable task due to the rapid growth in the number of texts in digital form available online. It aims to classify different texts, also...
[ "The Reuters-8 dataset (with stop words removed)" ]
7,839
qasper
bbf09514-3d80-4d9a-8530-7aa30e2168ca
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the hashtag and SemEval datasets contain only English data?\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 o...
[ "Yes" ]
5,418
qasper
c2829b90-949c-4460-b39d-7339c11cc4ce
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much does this model improve state-of-the-art?\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 units a...
[ "1 percent" ]
5,574
qasper
c9297747-fccb-4b62-bcd9-31ab62847d2f
[{"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
c92da270-3cbc-4e17-8cff-eb0e95416e5b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other examples of morphologically-rich languages do the authors give?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems. The...
[ "Russian" ]
4,026
qasper
cbbdddce-7f2b-4d2a-9546-d4107a06c2be
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the baseline?\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, estimate...
[ "QA PGNet, Multi-decoder QA PGNet with lookup table embedding" ]
6,487
qasper
db22c74c-7866-42e7-ace8-e84dfb150b3f
[{"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
eea02ea9-7aea-42ce-bfd7-04316ec6fe23
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which models/frameworks do they compare to?\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 including ...
[ "MLP" ]
4,145
qasper
00da4372-67ee-4b0f-b917-961832934026
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset is used?\n\nIntroduction \nThe new generation of Neural Machine Translation (NMT) systems is known to be extremely data hungry BIBREF0 . Yet, most existing NMT training pipelines fail to fully take advantage of the very l...
[ "Europarl corpus , WMT newstest 2014, News-Commentary-11, Wikipedia from WMT 2014, Multi-UN, EU-Bookshop, Rapid, Common-Crawl (WMT 2017)" ]
5,625
qasper
01c3cc62-eb0c-4f7f-8d9b-8542e158ab68
[{"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,...
[ "Wikipedia articles are labelled with one of six quality classes, in descending order of quality: Featured Article (“FA”), Good Article (“GA”), B-class Article (“B”), C-class Article (“C”), Start Article (“Start”), and Stub Article (“Stub”)., The quality class of a Wikipedia article is assigned by Wikipedia reviewe...
5,709
qasper