uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
3f36c106-64c3-490b-83a9-09c4d8c86a61 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their framework automatically optimize for hyperparameters?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaigns ... | [
"Unanswerable"
] | 5,748 | qasper |
3fb00bef-bda5-4eee-99e3-763ff229faa1 | [{"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... | [
"De-En, En-Fr, Fr-En, En-Es, Ro-En, En-De, Ar-En, En-Ru"
] | 5,431 | qasper |
4087772c-f964-4af8-a1d7-b1304daac336 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what data did they use?\n\nIntroduction\nLong short term memory (LSTM) units BIBREF1 are popular for many sequence modeling tasks and are used extensively in language modeling. A key to their success is their articulated gating struct... | [
"Penn Treebank (PTB) , WikiText2 (WT-2)"
] | 4,613 | qasper |
62018462-2cb4-45ec-833a-83b9b0e56db2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline is used in the experiments?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural language processing. Early such systems were mostly built using markup languages s... | [
"various versions of LiLi as baselines, Single, Sep, F-th, BG, w/o PTS"
] | 8,578 | qasper |
679548cd-b69e-4944-9772-c1facb5a3d7f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the data used for training annotated?\n\nIntroduction\nWhat would be possible if a person had an oracle that could immediately provide the answer to any question about the visual world? Sight-impaired users could quickly and re... | [
"The number of redundant answers to collect from the crowd is predicted to efficiently capture the diversity of all answers from all visual questions."
] | 5,052 | qasper |
684350e9-b412-4fb6-93d0-510d57942459 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the model performance on target language reading comprehension?\n\nIntroduction\nReading Comprehension (RC) has become a central task in natural language processing, with great practical value in various industries. In recent ... | [
"when testing on English, the F1 score of the model training on Chinese (Zh) is 53.8, F1 score is only 44.1 for the model training on Zh-En"
] | 3,417 | qasper |
6a9b13fe-16b9-4923-bd53-938935ed258a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language do they explore?\n\nWinograd Schemas\nA Winograd schema (Levesque, Davis, and Morgenstern 2012) is a pair of sentences, or of short texts, called the elements of the schema, that satisfy the following constraints:\nThe f... | [
"English, French, German "
] | 3,339 | qasper |
6adeeb44-c3a4-4e5c-90e6-ab78f3c61afc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does the TextWorld ACG dataset contain?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level mea... | [
"Unanswerable"
] | 6,248 | qasper |
6f4a8a03-9b23-4be9-a749-9a08d8fbb31b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation metrics are reported?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with civil law sys... | [
"precision, recall, F1 , accuracy "
] | 5,474 | qasper |
7cd9ee19-bd63-487a-a954-3d27f70ba27a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What architecture does the encoder have?\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... | [
"LSTM"
] | 3,047 | qasper |
7fcc21e5-9802-412b-ae4f-ccec245bd311 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What profile metadata is used for this analysis?\n\nIntroduction\nUser profiles on social media platforms serve as a virtual introduction of the users. People often maintain their online profile space to reflect their likes and values... | [
"username, display name, profile image, location, description"
] | 6,809 | qasper |
89d78e96-c931-4078-8db7-270a6cfe8bae | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline is used?\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 emotion. If machi... | [
"Wang et al. , maximum entropy classifier with bag of words model"
] | 3,187 | qasper |
b085a17b-ef7d-4303-a314-b85a5af83c26 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they test their framework performance on commonly used language pairs, such as English-to-German?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in r... | [
"Yes"
] | 5,758 | qasper |
b3028743-888c-4ba4-85ca-b5b380f208db | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What limitations do the authors demnostrate of their model?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and dry c... | [
"Since we do not have an end-to-end dataset, the generated English poem may not work well with Shakespeare style transfer"
] | 2,142 | qasper |
c7731ed6-de5c-47d2-8b98-d4e9602cc1c9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are 10 other phenotypes that are annotated?\n\nIntroduction and Related Work\nWith the widespread adoption of electronic health records (EHRs), medical data are being generated and stored digitally in vast quantities BIBREF0. Whi... | [
"Adv. Heart Disease, Adv. Lung Disease, Alcohol Abuse, Chronic Neurologic Dystrophies, Dementia, Depression, Developmental Delay, Obesity, Psychiatric disorders and Substance Abuse"
] | 2,187 | qasper |
cc4009c3-1e6e-4bd8-bc2f-bdbd825a0739 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the algorithm used to create word embeddings?\n\nIntroduction\nNatural languages evolve and words have always been subject to semantic change over time BIBREF1. With the rise of large digitized text resources recent NLP techno... | [
"Unanswerable"
] | 2,624 | qasper |
d54bb29f-fe20-45ef-8a2c-223aa38da094 | [{"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... | [
"No"
] | 5,709 | qasper |
df608466-a070-4f28-a0fc-17cbec2d29aa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they combine a deep learning model with a knowledge base?\n\nIntroduction\nNamed entity recognition (NER) BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 is the process by which we identify text spans which mention named entities, and to... | [
"ELMo embeddings are then used with a residual LSTM to learn informative morphological representations from the character sequence of each token"
] | 3,161 | qasper |
e16bbe07-24e3-413a-bae8-c29b84bbf25f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which approaches have been applied to solve word segmentation in Vietnamese?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural language ... | [
"Maximum Entropy, Weighted Finite State Transducer (WFST), support vector machines (SVM), conditional random fields (CRF)"
] | 4,686 | qasper |
ea4a5140-a7cb-495f-b0d0-5ffa6b8387a7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What annotations are present in dataset?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding systems for political science, opinion rese... | [
"answer each question with either `yes', `rather yes', `rather no', or `no'., can supplement each answer with a comment of at most 500 characters"
] | 4,997 | qasper |
f30a5663-7036-403b-9829-cbfff7524b28 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What limitations do the authors demnostrate of their model?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and dry c... | [
"we do not have an end-to-end dataset, the generated English poem may not work well with Shakespeare style transfer as shown in Figure FIGREF12 for \"Starry Night\" with a low average content score"
] | 2,142 | qasper |
fb8dd4b6-88f1-4561-83a6-2f2cb6919e90 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the model architecture used?\n\nIntroduction\nWhat would be possible if a person had an oracle that could immediately provide the answer to any question about the visual world? Sight-impaired users could quickly and reliably f... | [
"random forest, The question is encoded with a 1024-dimensional LSTM model that takes in a one-hot descriptor of each word in the question. The image is described with the 4096-dimensional output from the last fully connected layer of the Convolutional Neural Network (CNN), VGG16 BIBREF25 . The system performs an e... | 5,050 | qasper |
04077504-c8dc-4a4b-a09d-22ce0c7772fb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which translation systems do they compare against?\n\nIntroduction\nNumerous lexical semantic properties are captured by representations encoding distributional properties of words, as has been demonstrated in a variety of tasks BIBRE... | [
" English-Spanish MT system "
] | 5,397 | qasper |
0a80f82f-99be-4ecb-a54f-cdba44723ba7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were the baselines?\n\nIntroduction\nConventional automatic speech recognition (ASR) systems typically consist of several independently learned components: an acoustic model to predict context-dependent sub-phoneme states (senone... | [
"Unanswerable"
] | 2,754 | qasper |
103f52c2-4cd6-4147-ad4a-d4bf2c82298e | [{"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 |
185f9147-49bc-4922-a30d-ebffa86d6e9d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which real-world datasets are used?\n\nIntroduction\nEvent detection on microblogging platforms such as Twitter aims to detect events preemptively. A main task in event detection is detecting events of predetermined types BIBREF0, suc... | [
"cyber security (CyberAttack), death of politicians (PoliticianDeath)"
] | 6,673 | qasper |
1c03da04-c8f8-4c90-8679-c83dd108bfac | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used to assess the performance of the system?\n\nIntroduction\nTopic identification (topic ID) on speech aims to identify the topic(s) for given speech recordings, referred to as spoken documents, where the topics ar... | [
"Switchboard Telephone Speech Corpus BIBREF21, LORELEI (Low Resource Languages for Emergent Incidents) Program"
] | 4,765 | qasper |
3ba15b70-ab2b-4206-a985-0f3eea083cc7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much higher quality is the resulting annotated data?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the re... | [
"improvement when the difficult subset with expert annotations is mixed with the remaining crowd annotation is 3.5 F1 score, much larger than when a random set of expert annotations are added"
] | 5,761 | qasper |
3bda84b2-92a2-4a36-a9ba-abbe46cc652e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the source of the news articles?\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 t... | [
"The BreakingNews dataset"
] | 3,080 | qasper |
5590eafb-521c-4abf-b36e-c4776fe43379 | [{"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 expected number of unique outputs a word recognition system assigns to a set of adversarial perturbations "
] | 5,904 | qasper |
57736668-e894-487c-903e-e0b12ad4f6bf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How successful are the approaches used to solve word segmentation in Vietnamese?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural langu... | [
"Their accuracy in word segmentation is about 94%-97%."
] | 4,687 | qasper |
64907ea0-eb07-4baf-8a0a-082877402358 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What two metrics are proposed?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level meaning and highl... | [
"average unique predictions, randomly sample 2000 decoder hidden states at INLINEFORM4 steps following a delimiter ( INLINEFORM5 ) and apply an unsupervised clustering method (t-SNE BIBREF35 )"
] | 6,244 | qasper |
678ef2a3-1563-46eb-9bd1-b73c40a23c15 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What interface does Macaw currently have?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy... | [
"The current implementation of Macaw supports a command line interface as well as mobile, desktop, and web apps."
] | 2,271 | qasper |
72897b22-9a84-4131-ae30-2d1c1425e951 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for evaluation?\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, furnitur... | [
"BLEU-4, NIST-4, ROUGE-4"
] | 5,867 | qasper |
73e7823d-e024-44ee-be57-f3be10a3d275 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is best BLEU score of language style transfer authors got?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and d... | [
"average target BLEU score of 29.65"
] | 2,143 | qasper |
7809750d-3979-45ca-8e1c-07d33b16a088 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are similarities and differences between the texts from violent and non-violent religious groups analyzed?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Internet to spread its... | [
"A comparison of common words, We aggregated the score for each word and normalized each article by emotions. To better compare the result, we added a baseline of 100 random articles from a Reuters news dataset as a non-religious general resource"
] | 4,679 | qasper |
7b60030f-98a9-40f3-ac90-188945be6ce7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many training samples do you have for training?\n\nIntroduction\nFrom a group of small users at the time of its inception in 2009, Quora has evolved in the last few years into one of the largest community driven Q&A sites with div... | [
"Unanswerable"
] | 2,009 | qasper |
952bc520-6dfb-4da5-a10d-20097823dae3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use graphical models?\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, this ... | [
"No"
] | 4,220 | qasper |
961b605b-f98e-4e98-957b-7aecfdcb6faf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what language are the tweets?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most common stra... | [
"English "
] | 3,084 | qasper |
99c82850-4bd3-41cc-bb0e-a4d8c93959aa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the new dataset?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most common ... | [
"14,100 tweets"
] | 3,086 | qasper |
a7071049-fa16-4fdf-bdc8-c88077a4ab08 | [{"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,... | [
"Unanswerable"
] | 3,953 | qasper |
a8e217a6-8b12-42d7-a69a-90798cb62ec8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they recommend translating the premise and hypothesis together?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect ... | [
"No"
] | 5,516 | qasper |
ac383416-b69b-47f2-8b32-a6bda508be4a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the combination of rewards for reinforcement learning?\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 intended meaning of... | [
"irony accuracy, sentiment preservation"
] | 6,082 | qasper |
b4be9fe3-cc75-431e-b493-a7fe9fae5b95 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What TIMIT datasets are used for testing?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Word2Vec BIBREF0 and GloveBIBREF1. The re... | [
" this paper makes use of the official training and test sets, covering in total 630 speakers with 8 utterances each"
] | 5,207 | qasper |
bad7349f-629c-413d-af92-c01f35c3f40d | [{"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"
] | 5,082 | qasper |
bb275ef7-fed6-4833-b80a-464da21b2cd4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the tweets annotated?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually define... | [
"tweets are annotated with only Favor or Against for two targets - Galatasaray and Fenerbahçe"
] | 2,820 | qasper |
bc30d7b6-23d8-4abe-a556-1b9db0ea4103 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On what datasets are experiments performed?\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 and image BIBR... | [
"SQuAD"
] | 5,604 | qasper |
bd2ba25f-f4a4-4256-a701-83f39512ecab | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"why are their techniques cheaper to implement?\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 tak... | [
"They do not require the availability of a backward translation engine."
] | 5,628 | qasper |
c528d849-9e89-4521-bdd9-b245d7276d21 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Were other baselines tested to compare with the neural baseline?\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 ... | [
"SVM, No-Answer Baseline (NA) , Word Count Baseline, Human Performance"
] | 5,283 | qasper |
cb099f95-442f-4de9-8c6f-9ba566eec415 | [{"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... | [
" Recurrent Neural Network (RNN)"
] | 2,237 | qasper |
cdfd89af-32e1-4ac6-be74-5baf00585078 | [{"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 , evaluation script, automatic evaluation, human evaluation, minimum edit evaluation, word error rate (WER), factual errors and their types, fluency issues, acceptability of the output for production use in a news agency"
] | 5,972 | qasper |
cea98821-e460-43dc-bfd5-e7771781a63b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is sensationalism scorer trained?\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 sum... | [
"classifying sensational and non-sensational headlines using a one-layer CNN with a binary cross entropy loss"
] | 6,345 | qasper |
d8cae2f3-5c1a-401f-8eb9-1e4c12cd1152 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many subjects does the EEG data come from?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIBREF0 , BIBREF1 . In particul... | [
"14"
] | 3,283 | qasper |
dab877d5-79f4-4887-9d96-ae1239cbb34c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what age range is in the data?\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 the availab... | [
"Unanswerable"
] | 5,099 | qasper |
fce5a5cc-0883-4784-80ba-cf23902afe35 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages do they use in their experiments?\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 data ... | [
"English, Spanish, Finnish"
] | 5,515 | qasper |
13f791c5-1fbd-4ff8-9ef2-b9d71e3ae5d5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"LDA is an unsupervised method; is this paper introducing an unsupervised approach to spam detection?\n\nIntroduction\nMicroblogging such as Twitter and Weibo is a popular social networking service, which allows users to post messages ... | [
"No"
] | 3,628 | qasper |
1cf6b50d-d14b-4eef-b001-cfe8a93263ae | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they define similar equations?\n\nIntroduction\nEquations are an important part of scientific articles, but many existing machine learning methods do not easily handle them. They are challenging to work with because each is uni... | [
"Similar words were ranked by computing Cosine distance between the embedding vector ( INLINEFORM0 ) representation of the query equation and the context vector representation of the words ( INLINEFORM1 ). Similar equations were discovered using Euclidean distance computed between the context vector representations... | 3,789 | qasper |
24fb7c5e-b1da-4a2e-ad65-1475a8d19c6f | [{"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 |
427c809d-4ee9-4763-8608-0d9d1459cd03 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the data de-identified?\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, est... | [
"Yes"
] | 6,489 | qasper |
51014e10-022a-498e-8142-e6447e9ac353 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many people participated in their evaluation study of table-to-text models?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 , BIBREF4 has seen a growth in... | [
"Unanswerable"
] | 5,088 | qasper |
53352a6a-5d52-4640-a16f-4b279e908dd6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the state of the art methods?\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.... | [
"Unanswerable"
] | 3,612 | qasper |
59552e68-8a4e-4a1b-b683-1d61b554f0d7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which evaluation methods are used?\n\nIntroduction\nSummarization of large texts is still an open problem in language processing. People nowadays have lesser time and patience to go through large pieces of text which make automatic su... | [
"Quantitative evaluation methods using ROUGE, Recall, Precision and F1."
] | 5,729 | qasper |
5ec7d8ab-c4bd-4cc6-89ac-b7bc841d1787 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where does the data come from?\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 ... | [
"crowsourcing platform"
] | 3,155 | qasper |
6002c42f-2239-49e7-84cb-b8358d163801 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What challenges do different registers and domains pose to this task?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively e... | [
"linguistic variability"
] | 20,058 | qasper |
80a73049-f279-4ec5-93cc-e3144ca0f512 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does KBQA abbreviate for\n\nIntroduction\nKnowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 . For an input question... | [
"Knowledge Base Question Answering"
] | 6,736 | qasper |
8290b048-0fe7-4647-bb2c-0667c3d13e1d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the Chinese 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 been w... | [
"32,595 posts"
] | 5,898 | qasper |
8ae362b4-bcbc-499d-b624-8d1e27ca516c | [{"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... | [
"Yes"
] | 10,902 | qasper |
a0ed4246-ddb7-44ed-89c5-57b3cc78b686 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they obtain the OSG 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 op... | [
"data has been developed by crawling and pre-processing an OSG web forum"
] | 4,715 | qasper |
a77f4bd3-8d55-40c8-9d90-5502a1fec643 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much does their model outperform existing models?\n\nIntroduction\nSingle-document summarization is the task of generating a short summary for a given document. Ideally, the generated summaries should be fluent and coherent, and s... | [
"On arXiv dataset, the proposed model outperforms baselie model by (ROUGE-1,2,L) 0.67 0.72 0.77 respectively and by Meteor 0.31.\n"
] | 5,768 | qasper |
a8268e37-67ad-491a-b346-90753bc018ba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the global network features which quantify different aspects of the sharing process?\n\nIntroduction and related work\nIn recent years there has been increasing interest on the issue of disinformation spreading on online soci... | [
"Number of Strongly Connected Components (SCC), Size of the Largest Strongly Connected Component (LSCC), Number of Weakly Connected Components (WCC), Size of the Largest Weakly Connected Component (LWCC), Diameter of the Largest Weakly Connected Component (DWCC), Average Clustering Coefficient (CC), Main K-core Num... | 6,635 | qasper |
b4d8d150-56c4-40dc-85e7-d220dc6e3281 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the model performance on target language reading comprehension?\n\nIntroduction\nReading Comprehension (RC) has become a central task in natural language processing, with great practical value in various industries. In recent ... | [
"Table TABREF6, Table TABREF8"
] | 3,417 | qasper |
ba15fd95-3abd-4d8a-947f-b81f1ed0d4c8 | [{"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... | [
"training set has 89,042 sentence pairs, and the test set has 100 pairs, training set contains 296,402, 2,000 for development and 359 for testing"
] | 3,186 | qasper |
ba303677-1685-4f18-97e1-68849b99cded | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which existing benchmarks did they compare to?\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 b... | [
"Affective Text, Fairy Tales, ISEAR"
] | 4,373 | qasper |
bb8c6abb-4a78-43c4-85df-6a7786146260 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does this model overcome the assumption that all words in a document are generated from a single event?\n\nIntroduction\nWith the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter)... | [
"by learning a projection function between the document-event distribution and four event related word distributions "
] | 5,507 | qasper |
c015c441-0c73-4bf3-8c9d-3fd0d11e1b20 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset was used?\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 have a ... | [
"48,705 e-books from 13 publishers, search query logs of 21,243 e-books for 12 months"
] | 4,423 | qasper |
c06b1be5-6603-4885-a13b-df5c259da226 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they select instances to their hold-out test set?\n\nProblem Statement\nSpoken conversations still remain the most natural and effortless means of human communication. Thus a lot of valuable information is conveyed and exchange... | [
"1264 instances from simulated data, 1280 instances by adding two out-of-distribution symptoms and 944 instances manually delineated from the symptom checking portions of real-word dialogues"
] | 4,631 | qasper |
c835a46c-3057-4c8d-ab77-9868a63485a5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of SFU Review corpus?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple use-cases, like systems t... | [
"Unanswerable"
] | 3,291 | qasper |
d79a9e18-ac07-4c62-b29d-a5fa88194e0a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is SemCor3.0 reflective of English language data in general?\n\nIntroduction\nWord Sense Disambiguation (WSD) is a fundamental task and long-standing challenge in Natural Language Processing (NLP), which aims to find the exact sense o... | [
"Unanswerable"
] | 3,008 | qasper |
e0d29b4e-16bd-4058-8587-4fe6a3f4d539 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the benchmark dataset?\n\nIntroduction\nVector-based semantic mapping models are used to represent textual structures (words, phrases, and documents) as high-dimensional meaning vectors. Typically, these models utilize textual... | [
"a benchmark dataset created by ceccarelli2013learning from the CoNLL 2003 data"
] | 5,383 | qasper |
e53d1a9e-1863-49d0-909b-03162e0f9785 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline for this task?\n\nIntroduction\nPropaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. In the Internet era, thanks to the mechanism of sharing in social networks, propaga... | [
"The baseline system for the SLC task is a very simple logistic regression classifier with default parameters. The baseline for the FLC task generates spans and selects one of the 18 techniques randomly."
] | 4,230 | qasper |
e5428348-e29f-4c06-9ab6-25477225eebc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used to train the model?\n\nIntroduction\nEarlier studies on stock market prediction are based on the historical stock prices. Later studies have debunked the approach of predicting stock market movements using histori... | [
"Collected tweets and opening and closing stock prices of Microsoft."
] | 3,163 | qasper |
e97fe6d0-6a83-423d-977b-4fa5872ac2d2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baselines?\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 for opinion increased, commer... | [
"majority baseline, lexicon-based approach"
] | 3,540 | qasper |
07e63204-b498-4555-9cb9-ff0d0fa11637 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which qualitative metric are used for evaluation?\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-... | [
"Relation Generation (RG), Content Selection (CS), Content Ordering (CO)"
] | 7,008 | qasper |
0ecdf5fe-85af-4373-8a88-4fdceb76b56d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the previous state of the art for this task?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quality education from reputed universities to students a... | [
"hLSTM"
] | 4,780 | qasper |
193f7069-1bba-4b67-bfdd-0b77726758e1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the data in the new corpus come sourced?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively examined from different... | [
"refer to each article, blog post, comment, or forum posts as a document"
] | 20,057 | qasper |
1f23ec2f-741f-4fcd-9f89-33941a027ffb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they train their model starting from a checkpoint?\n\nIntroduction\nThe ability of semantic reasoning is essential for advanced natural language understanding (NLU) systems. Many NLU tasks that take sentence pairs as input, such as... | [
"No"
] | 5,594 | qasper |
25127aae-cada-4003-8370-962aa99e43e0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What modern MRC gold standards are analyzed?\n\nIntroduction\nThere is a recent spark of interest in the task of Question Answering (QA) over unstructured textual data, also referred to as Machine Reading Comprehension (MRC). This is ... | [
"MSMARCO, HOTPOTQA, RECORD, MULTIRC, NEWSQA, and DROP."
] | 6,561 | qasper |
3303bade-c818-49d9-886c-2396a15e2d2d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets are used in the experiment?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with civil law... | [
"build a new one, collect INLINEFORM0 cases from China Judgments Online"
] | 5,476 | qasper |
33543e6b-6fb9-4b2e-9fa6-73f85246ad72 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many tweets did they collect?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually def... | [
"700 "
] | 2,821 | qasper |
3e758f1f-1e25-4901-b0f9-0d6ac3a390d8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the baselines?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level meaning and highlight c... | [
"CopyRNN (Meng et al., 2017), Multi-Task (Ye and Wang, 2018), and TG-Net (Chen et al., 2018b)"
] | 6,244 | qasper |
40243a79-0148-44e5-ad1d-5cb0bb5986f2 | [{"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... | [
"NBOW, LSTM, attentive LSTM"
] | 5,216 | qasper |
403437f8-45e4-40d6-846b-ff5554c29532 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they match annotators to instances?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the requisite domain... | [
"Annotations from experts are used if they have already been collected."
] | 5,760 | qasper |
58e62fee-c1b7-4a62-8266-0290b991257c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the average length of dialog?\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... | [
"4.5 turns per dialog (8533 turns / 1900 dialogs)"
] | 3,239 | qasper |
63bab5e2-1d19-4ed4-8ecb-56eab3a06bf2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators participated?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most common str... | [
"five annotators"
] | 3,083 | qasper |
69009085-66d6-4de6-b878-356a195d7a14 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What architecture does the decoder have?\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... | [
"LSTM"
] | 3,047 | qasper |
882f6088-93ce-4977-b524-948fef8c7a0a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they score phrasal compositionality?\n\nIntroduction\nNumerous lexical semantic properties are captured by representations encoding distributional properties of words, as has been demonstrated in a variety of tasks BIBREF0 , BI... | [
"Spearman's INLINEFORM0 between phrasal similarities derived from our compositional functions and the human annotators"
] | 5,399 | qasper |
88479af3-d293-4002-ab02-b119aba30a28 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the domain of the corpus?\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 transc... | [
"telephone calls"
] | 2,066 | qasper |
98947161-bdd7-49a2-9bf1-d00ee0f94919 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages do they use?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, including essay scoring (q... | [
"English"
] | 5,705 | qasper |
a1092ccc-a2e7-4481-8b73-23933418561a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is fine-tuning required to incorporate these embeddings into existing models?\n\nIntroduction\nKnowledge graphs BIBREF0 enable structured access to world knowledge and form a key component of several applications like search engines, ... | [
"No"
] | 6,216 | qasper |
a13b011b-8066-48ef-af02-98c908fdd2f7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the real-life dataset?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their workforce. The PA proc... | [
"26972"
] | 4,197 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.