uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
30bb550b-c7c6-42bf-b77a-e5fbc676ec0b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they control for annotation artificats?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly provided), requires bringing to bea... | [
"Choice-Only model, which is a variant of the well-known hypothesis-only baseline, Choice-to-choice model, tries to single out a given answer choice relative to other choices, Question-to-choice model, in contrast, uses the contextual representations for each question and individual choice and an attention model At... | 9,202 | qasper |
39797a71-4723-43d9-8a82-b6ce339d71fb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the tagging scheme employed?\n\nIntroduction\nThere exists a class of language construction known as pun in natural language texts and utterances, where a certain word or other lexical items are used to exploit two or more sep... | [
"a new tagging scheme consisting of three tags, namely { INLINEFORM0 }"
] | 3,833 | qasper |
44ff35b5-afb5-43ae-89ec-b042678dbc43 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the sequential nature of the story captured?\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 ... | [
"we provide the decoder with the context of the whole sequence and the content of the current image (i.e. global and local information) to generate the corresponding text that will contribute to the overall story"
] | 1,775 | qasper |
519d7ca1-31ed-4001-856e-5ae83c089773 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are improvements for these two approaches relative to ELMo-only baselines?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs... | [
"only modest gains on three of the four downstream tasks"
] | 3,689 | qasper |
53e876f4-cea5-4c6b-b7a6-e8d00a7801bc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they obtain the interactions?\n\nIntroduction\nIn the kitchen, we increasingly rely on instructions from cooking websites: recipes. A cook with a predilection for Asian cuisine may wish to prepare chicken curry, but may not kn... | [
"from Food.com"
] | 3,949 | qasper |
89e0ad57-b645-4046-b80e-75f584e1c49d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the political bias of different sources included in the model?\n\nIntroduction and related work\nIn recent years there has been increasing interest on the issue of disinformation spreading on online social media. Global concern... | [
"By assigning a political bias label to each news article and training only on left-biased or right-biased outlets of both disinformation and mainstream domains"
] | 6,633 | qasper |
961ed2ac-5e55-4f77-a3c8-88a18f1cdf8d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they calculate a static embedding for each word?\n\nIntroduction\nThe application of deep learning methods to NLP is made possible by representing words as vectors in a low-dimensional continuous space. Traditionally, these wor... | [
" by taking the first principal component (PC) of its contextualized representations in a given layer"
] | 6,137 | qasper |
96a44861-1031-447d-acd1-9b082860c814 | [{"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 |
a1a1978f-e8a5-47c2-b37d-f5d6caea7403 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators participated?\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 system for cancer d... | [
"Unanswerable"
] | 2,755 | qasper |
b3f1c7b5-816e-454c-9429-697b03d97444 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What hyperparameters are explored?\n\nIntroduction\nThere have been many implementations of the word2vec model in either of the two architectures it provides: continuous skipgram and CBoW (BIBREF0). Similar distributed models of word ... | [
"Hyperparameters explored were: dimension size, window size, architecture, algorithm and epochs."
] | 3,342 | qasper |
b9ab79f9-c549-47b7-a104-da743d37e638 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data do they look at?\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 follo... | [
"WSC collection"
] | 3,340 | qasper |
d552922a-491f-45a3-bdfe-1a806de97221 | [{"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 and sentiment preservation"
] | 6,082 | qasper |
d5f7db13-b442-4e14-961b-21748eaebe4c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks were evaluated?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data has beco... | [
"ReviewQA's test set"
] | 4,699 | qasper |
e0008f07-b7bd-4d44-8a76-56b839caf036 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they experiment with other tasks?\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 Langu... | [
"No"
] | 3,588 | qasper |
e130e913-6d69-4190-836e-0c851f24ff9a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What model is used to encode the images?\n\nIntroduction\nOver the past few years, generating text from images and videos has gained a lot of attention in the Computer Vision and Natural Language Processing communities and several rel... | [
"a Convolutional Neural Network (CNN)"
] | 1,774 | qasper |
ee53705b-68ae-43ce-8b00-0ee8a409904b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors conduct experiments on the tasks mentioned?\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 f... | [
"Yes"
] | 3,343 | qasper |
013b4e61-76b1-4c86-895a-100243e932a4 | [{"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 |
20f71a03-93d6-41d6-81da-98a4c5a01efa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments do they use to quantify the extent of interpretability?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building b... | [
"semantic category-based approach"
] | 8,087 | qasper |
230145cf-e280-4d1c-9480-047d88f2bf08 | [{"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 ... | [
"Dataset contains total of 14100 annotations."
] | 3,086 | qasper |
23914902-2799-4575-958b-c03bba805d11 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much does their best model outperform the state-of-the-art?\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>... | [
"Best proposed model achieves F1 score of 84.9 compared to best previous result of 84.1."
] | 3,324 | qasper |
44117667-d51a-49f7-9e03-78991211d80d | [{"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,... | [
"F1, precision, recall, accuracy"
] | 4,221 | qasper |
6c498ed2-0f6a-4175-8584-9cc1d55fd720 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a second order co-ocurrence matrix?\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 – INLI... | [
"The matrix containing co-occurrences of the words which occur with the both words of every given pair of words."
] | 5,727 | qasper |
88cef777-453d-4f1a-b72e-ecf450e55e79 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What approaches do they use towards text analysis?\n\nIntroduction\nIn June 2015, the operators of the online discussion site Reddit banned several communities under new anti-harassment rules. BIBREF0 used this opportunity to combine ... | [
"Modeling considerations: the variables (both predictors and outcomes) are rarely simply binary or categorical; using a particular classification scheme means deciding which variations are visible,; Supervised and unsupervised learning are the most common approaches to learning from data; the unit of text that ... | 10,570 | qasper |
8b0d9fe9-1046-4cce-8bdb-ab3c11d4d23c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"IS the graph representation supervised?\n\nIntroduction\nThe availability of massive electronic health records (EHR) data and the advances of deep learning technologies have provided unprecedented resource and opportunity for predicti... | [
"The graph representation appears to be semi-supervised. It is included in the learning pipeline for the medical recommendation, where the attention model is learned. (There is some additional evidence that is unavailable in parsed text)"
] | 6,104 | qasper |
8b43e560-f64c-4984-8127-e521a0de5897 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is their MNER SnapCaptions dataset?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opinions and preferences of groups and individuals. These insights are pr... | [
"10000"
] | 5,443 | qasper |
8c8ad4ad-9fee-4b23-b3ca-457a88cf6d12 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the spatial aspect of the EEG signal computed?\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 ... | [
"They use four-layered 2D CNN and two fully connected hidden layers on the channel covariance matrix to compute the spatial aspect."
] | 3,284 | qasper |
98af2287-098d-4417-a9b2-dd497961c4b9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what cases is attention different from alignment?\n\nIntroduction\nNeural machine translation (NMT) has gained a lot of attention recently due to its substantial improvements in machine translation quality achieving state-of-the-ar... | [
"most word alignments only involve one or a few words, attention can be distributed more freely"
] | 4,378 | qasper |
a10b1cb8-5e21-4d2f-baef-41b87e843c3a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the existing biases?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interactions among use... | [
"sampling tweets from specific keywords create systematic and substancial racial biases in datasets"
] | 5,696 | qasper |
a77736e3-1e75-4c9c-8ff9-7e447bacf46a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline systems are proposed?\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 Langua... | [
"Conditional Random Fields, BiLSTM-CRF, Multi-Task Learning, BioBERT"
] | 3,587 | qasper |
a7917c51-27b4-45dd-94d2-65db202cbf81 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the dataset feature only English language data?\n\nIntroduction\nAbusive language refers to any type of insult, vulgarity, or profanity that debases the target; it also can be anything that causes aggravation BIBREF0 , BIBREF1 . ... | [
"Unanswerable"
] | 2,920 | qasper |
b27b66aa-0158-4cc2-b1eb-d18c84f9a3a7 | [{"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... | [
"(c) previous best model trained on S-SQuAD BIBREF5 by using Dr.QA BIBREF20 "
] | 3,113 | qasper |
b63912aa-be0c-45b4-89a5-e0f8c6227bdc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What existing approaches do they compare to?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interac... | [
"Waseem and Hovy BIBREF5, Davidson et al. BIBREF9, and Waseem et al. BIBREF10"
] | 5,698 | qasper |
becada8b-99c6-4cc7-ae29-41153c9dad54 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which corpora does this paper analyse?\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 wome... | [
"ESTER1, ESTER2, ETAPE, REPERE"
] | 5,375 | qasper |
c2788179-e9d3-48b8-8938-7e6a80b3a3ff | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the 18 propaganda techniques?\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, propa... | [
"Loaded language, Name calling or labeling, Repetition, Exaggeration or minimization, Doubt, Appeal to fear/prejudice, Flag-waving, Causal oversimplification, Slogans, Appeal to authority, Black-and-white fallacy, dictatorship, Thought-terminating cliché, Whataboutism, Reductio ad Hitlerum, Red herring, Bandwagon,... | 4,231 | qasper |
ded36678-ef5a-4c11-b623-885915b0cbe4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Were any of the pipeline components based on deep learning models?\n\nIntroduction\nThe automatic identification, extraction and representation of the information conveyed in texts is a key task nowadays. In fact, this research topic ... | [
"No"
] | 3,010 | qasper |
e3e08551-819f-4606-8e1b-7d275fef50fb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is model compactness measured?\n\nIntroduction\nAccurate grapheme-to-phoneme conversion (g2p) is important for any application that depends on the sometimes inconsistent relationship between spoken and written language. Most promi... | [
"Using file size on disk"
] | 4,277 | qasper |
fbe608e1-4b32-47b8-a6b9-2d3c0debecfa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they compare lexicons?\n\nIntroduction\nSentiment analysis aims to uncover the emotion conveyed through information. In online social networks, sentiment analysis is mainly performed for political and marketing purposes, produc... | [
"Human evaluators were asked to evaluate on a scale from 1 to 5 the validity of the lexicon annotations made by the experts and crowd contributors."
] | 6,752 | qasper |
03c0ab7d-a1f3-42d0-92f3-3d866533ab9d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much is performance improved on NLI?\n\nIntroduction\nThe ability of semantic reasoning is essential for advanced natural language understanding (NLU) systems. Many NLU tasks that take sentence pairs as input, such as natural lang... | [
"The average score improved by 1.4 points over the previous best result."
] | 5,593 | qasper |
079870fe-7b9a-4870-aa37-822a731aa01e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are labels in car speak language dataset?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car dealer listens... | [
"the car"
] | 2,205 | qasper |
087deb43-9fa1-4267-af61-f0056127ff36 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what methods were used to reduce data sparsity effects?\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 E... | [
"data augmentation"
] | 5,567 | qasper |
1561d536-5154-4759-812c-4ea25b715a1a | [{"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... | [
"8,275 sentences and 167,739 words in total"
] | 3,587 | qasper |
211e35df-a8fc-42d1-9118-d9dd9cf81b11 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nWith the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter) and news media sites (e.g. Google news) have become important ... | [
"Unanswerable"
] | 5,496 | qasper |
2515b5df-e9e9-4fdf-b644-dc7278fd577f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what linguistics features are used?\n\nIntroduction\nModern Standard Arabic (MSA) and Classical Arabic (CA) have two types of vowels, namely long vowels, which are explicitly written, and short vowels, aka diacritics, which are typica... | [
"POS, gender/number and stem POS"
] | 7,072 | qasper |
2ff21986-ce7e-4567-9f74-79a5e954ee23 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they inspect their model to see if their model learned to associate image parts with words related to entities?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opin... | [
"Yes"
] | 5,453 | qasper |
3d54adbc-1d34-4e30-82bc-d529168f1c08 | [{"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... | [
"standard ROGUE metric, Recall, Precision and INLINEFORM0 scores for ROGUE-1, INLINEFORM2 scores for ROGUE-2 and ROGUE-L"
] | 5,729 | qasper |
493f0b95-a6f3-4d43-8ae5-a5c9d2794813 | [{"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... | [
"Word Content (WC) probing task, Depth (Dep) and Top Constituent (TopC) (of the input sentence's constituent parse tree) probing tasks"
] | 3,416 | qasper |
4e435568-878b-4a93-9a2a-ff7d98c43164 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the pivot-based baselines?\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... | [
"firstly translates a source language into the pivot language which is later translated to the target language"
] | 5,433 | qasper |
51643fa3-0f8b-46da-b590-d14eae264daf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the baseline?\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 othersBIBREF0. There... | [
"CNN modelBIBREF0, Stanford CRF modelBIBREF21"
] | 4,284 | qasper |
737d1df5-1252-4d48-9b37-77e5f77e6a46 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What source-target language pairs were used in this work? \n\nIntroduction\nReading Comprehension (RC) has become a central task in natural language processing, with great practical value in various industries. In recent years, many l... | [
"English , Chinese"
] | 3,418 | qasper |
7531cc3a-258b-49f9-b0cf-824212911ca7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metric is used?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known then the ap... | [
"average classification accuracy"
] | 2,608 | qasper |
99fe2859-fccf-422a-9934-6d78fe2f5195 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of this dataset?\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 platfor... | [
"23,700 "
] | 3,156 | qasper |
9d027a42-efe5-4eba-b8d6-534772ac1215 | [{"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 (... | [
"non-domain-adaptive baseline with bag-of-words representations and SVM classifier, mSDA, non-domain-adaptive CNN trained on source domain, neural model that exploits auxiliary tasks, adversarial training to reduce representation difference between domains, variants of deep CNNs are used for encoding images and the... | 6,773 | qasper |
a8003072-da4e-4508-abe5-093eac7612a5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What semi-supervised learning is applied?\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 cur... | [
"first a model is trained on the training set and then this model is used to predict the labels of the silver data, This silver data is then simply added to our training set, after which the model is retrained"
] | 3,100 | qasper |
adc87d69-3c01-43f9-85a7-22851d51e668 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the G-BERT model useful beyond the task considered?\n\nIntroduction\nThe availability of massive electronic health records (EHR) data and the advances of deep learning technologies have provided unprecedented resource and opportuni... | [
"There is nothing specific about the approach that depends on medical recommendations. The approach combines graph data and text data into a single embedding."
] | 6,110 | qasper |
bd21311a-fdc6-4b04-bf14-ee6f9d5b1598 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Can named entities in SnapCaptions be discontigious?\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... | [
"Unanswerable"
] | 5,444 | qasper |
cd24a80d-070e-4c14-8aee-b29964d0db5a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a second order co-ocurrence matrix?\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 – INLI... | [
"frequencies of the other words which occur with both of them (i.e., second order co–occurrences)"
] | 5,727 | qasper |
d33d6fd4-66bd-45cf-8a01-8a62dd1bb251 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where are the hotel reviews from?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data h... | [
"TripAdvisor"
] | 4,701 | qasper |
e1ca79a6-ddb8-43c7-b2d7-853c7c92fe16 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which text embedding methodologies are used?\n\nIntroduction\nThe vast amounts of data collected by healthcare providers in conjunction with modern data analytics techniques present a unique opportunity to improve health service provi... | [
"Doc2Vec, PV-DBOW model"
] | 11,281 | qasper |
e58aa269-ec27-4dec-a4c8-47b0685ebb37 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other languages did they translate the data from?\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... | [
"English"
] | 3,102 | qasper |
f23f8f7d-3dd4-4d11-a435-3c3830ba445f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What useful information does attention capture?\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 per... | [
"it captures other information rather than only the translational equivalent in the case of verbs"
] | 4,376 | qasper |
090b4516-dc33-4a04-9627-0822940de0e0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used?\n\nIntroduction\nSummarization of patient information is essential to the practice of medicine. Clinicians must synthesize information from diverse data sources to communicate with colleagues and provide coord... | [
"MIMIC-III"
] | 3,944 | qasper |
1425e588-6cd3-4ad9-bf1d-4d1087eeae2f | [{"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... | [
"politics, business, science, and AskReddit, and 1000 additional posts from the Reddit frontpage. "
] | 5,756 | qasper |
1c3219a0-6f5f-490d-9436-5da7d3e5fb75 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a wizard of oz setup?\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 their infor... | [
"a setup where the seeker interacts with a real conversational interface and the wizard, an intermediary, performs actions related to the seeker's message"
] | 2,271 | qasper |
2adfd45a-0683-4538-93b0-61fe834bb10a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the two large-scale datasets used?\n\nIntroduction and related work\nIn recent years there has been increasing interest on the issue of disinformation spreading on online social media. Global concern over false (or \"fake\") ... | [
"US dataset, Italian dataset"
] | 6,629 | qasper |
31480381-c18f-4625-91ea-d179f29c2036 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which of the three pretraining tasks is the most helpful?\n\nIntroduction\nLarge pre-trained language models BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4 improved the state-of-the-art of various natural language understanding (NLU) tas... | [
"SR"
] | 6,839 | qasper |
4a4f2fdb-3b13-4fcc-b53d-a8d2a41d0216 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages are similar to each other?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known ... | [
"Nguni languages (zul, xho, nbl, ssw), Sotho languages (nso, sot, tsn)"
] | 2,610 | qasper |
4cccde9d-b01a-4bc9-ac26-9687bfe98427 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the dataset collected?\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 automate... | [
"Used from science exam questions of the Aristo Reasoning Challenge (ARC) corpus."
] | 8,026 | qasper |
4ddd956f-a8dd-487c-9ee5-b91bae5c5b7a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other models do they compare to?\n\nIntroduction\nPre-training of language models has been shown to provide large improvements for a range of language understanding tasks BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . The key idea is to... | [
"BIBREF11 , BIBREF26 "
] | 2,668 | qasper |
4ef30a65-016e-4f52-8e30-6c73bf1e4e85 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What extracted features were most influencial on performance?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and aim individua... | [
"Linguistic"
] | 2,438 | qasper |
5095aee9-8fae-4c2f-bcc7-408ed1d3a33b | [{"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 and accuracy"
] | 5,474 | qasper |
5435645c-ef75-46d4-b374-93ad07e6257d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What summarization algorithms did the authors experiment with?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their wo... | [
"LSA, TextRank, LexRank and ILP-based summary."
] | 4,197 | qasper |
5659cfec-a846-4770-a8be-d338cb4a8d5e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does the neural network architecture accomodate an unknown amount of senses per word?\n\nIntroduction\nWord Sense Disambiguation (WSD) is a fundamental task and long-standing challenge in Natural Language Processing (NLP), which a... | [
"converts WSD to a sequence learning task, leverage gloss knowledge, by extending gloss knowledge"
] | 3,010 | qasper |
5a58d46c-d932-4ace-8e42-121d6523e54c | [{"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... | [
"lacks of complete review approaches, datasets and toolkits "
] | 4,685 | qasper |
706ec765-0c63-407b-956d-60f03a511be4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What predictive model do they build?\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 behavior... | [
"logistic regression models based on unigram bag-of-words features (BOW), sentiment signals (SENT), the linguistic features from our earlier analyses (LING), and combinations of these features."
] | 5,755 | qasper |
7489348a-9de1-43ff-a709-944109a19497 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what language is the data in?\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 th... | [
"English , German, French"
] | 5,627 | qasper |
7970fb6b-869a-4e41-988a-87d90b83ad2e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data was presented to the subjects to elicit event-related responses?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIB... | [
"7 phonemic/syllabic ( /iy/, /piy/, /tiy/, /diy/, /uw/, /m/, /n/ ) as well as 4 words(pat, pot, knew and gnaw)"
] | 3,287 | qasper |
9b5ce756-4369-4590-a8a3-b88e961e5deb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the improvement over state-of-the-art statistically significant?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect... | [
"Yes"
] | 5,517 | qasper |
ae2b02cc-7e03-4d9d-9537-4f62cf1ed9c8 | [{"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... | [
"crawling and pre-processing an OSG web forum"
] | 4,715 | qasper |
b3d4318a-c179-4aeb-a56d-556db31b29ed | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline?\n\nIntroduction\nAutomatic classification of sentiment has mainly focused on categorizing tweets in either two (binary sentiment analysis) or three (ternary sentiment analysis) categories BIBREF0 . In this work ... | [
"SVMs, LR, BIBREF2"
] | 3,585 | qasper |
bd9e93b5-8ff4-4c73-94ff-38d5f84f0ea5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what competitive results did they obtain?\n\nIntroduction\nConventional automatic speech recognition (ASR) systems typically consist of several independently learned components: an acoustic model to predict context-dependent sub-phone... | [
"On WSJ datasets author's best approach achieves 9.3 and 6.9 WER compared to best results of 7.5 and 4.1 on nov93 and nov92 subsets.\nOn Hub5'00 datasets author's best approach achieves WER of 7.8 and 16.2 compared to best result of 7.3 and 14.2 on Switchboard (SWB) and Callhome (CHM) subsets."
] | 2,755 | qasper |
d136984e-c5be-4ce0-9191-94ccf812f98b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interac... | [
"Yes"
] | 5,699 | qasper |
d1ba11cb-0992-4aba-a421-a8b58f969f5c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the algorithm improve on the state-of-the-art methods?\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 ... | [
"Yes"
] | 2,614 | qasper |
d4ef0b47-71d7-4126-80e4-34d6650c002e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How better does new approach behave than existing solutions?\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 B... | [
"On Coin Collector, proposed model finds shorter path in fewer number of interactions with enironment.\nOn Cooking World, proposed model uses smallest amount of steps and on average has bigger score and number of wins by significant margin."
] | 6,938 | qasper |
dd5c53ea-9105-47ef-be32-4c9831ca7c6c | [{"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\"... | [
"BiLSTMBIBREF14, BiLSTM+CNNBIBREF20, BiLSTM+CRFBIBREF1, BiLSTM+CNN+CRFBIBREF2, CNN modelBIBREF0 and Stanford CRF modelBIBREF21"
] | 4,287 | qasper |
e122553e-ef13-4a71-b616-118f0b59d52a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What biases does their model capture?\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 a... | [
"Data annotation biases where tweet containing disrespectful words are annotated as hate or offensive without any presumption about the social context of tweeters"
] | 5,697 | qasper |
0d807829-70e8-4ccd-afd1-7f256a7d9deb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which baselines did they compare against?\n\nIntroduction\nOne of the most fundamental topics in natural language processing is how best to derive high-level representations from constituent parts, as natural language meanings are a f... | [
"Various tree structured neural networks including variants of Tree-LSTM, Tree-based CNN, RNTN, and non-tree models including variants of LSTMs, CNNs, residual, and self-attention based networks"
] | 8,133 | qasper |
184bbccb-0205-4f9c-a897-e575fe0667be | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was their system's performance?\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 a... | [
"accuracy and F1-score of 89.6% and 89.2%, respectively"
] | 4,410 | qasper |
1a8c348e-dcc3-4c92-8a45-e87e92e68195 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which natural language(s) are studied in this paper?\n\nIntroduction\nThe challenges of imbalanced classification—in which the proportion of elements in each class for a classification task significantly differ—and of the ability to g... | [
"Unanswerable"
] | 5,825 | qasper |
25df057a-8136-4cdd-8d46-07e5a0b88318 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators tagged each tweet?\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... | [
"One"
] | 7,104 | qasper |
415c3f25-18ce-4d73-b647-97c37f67c998 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the answers double (and not triple) annotated?\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... | [
"Yes"
] | 5,282 | qasper |
4a4cd37c-d2f4-411f-865e-f77e5afb2c0e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is car-speak language collection of abstract features that classifier is later trained on?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, ... | [
"No"
] | 2,212 | qasper |
52ee5450-5fa3-4ab3-9a7b-e4af29234fb7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of classifiers 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, such... | [
"probabilistic model"
] | 6,673 | qasper |
5dc909e4-e5ea-46db-804c-5cc6ccc39882 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics were used?\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 BIBR... | [
"Exact Match (EM) and Macro-averaged F1 scores (F1) "
] | 3,112 | qasper |
5f6ad5b4-9a63-476c-91e3-5ac5d25e12cc | [{"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 |
6c480263-1276-4ef6-8c07-5b1a8ea7dbbf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used?\n\nIntroduction\nSummarization of patient information is essential to the practice of medicine. Clinicians must synthesize information from diverse data sources to communicate with colleagues and provide coord... | [
"MIMIC-III"
] | 3,944 | qasper |
81111149-924a-49f4-bf73-c2df13e6a3b1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they perform multilingual training?\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... | [
"by randomly alternating between languages for every new minibatch"
] | 3,048 | qasper |
81c709bb-9c27-4b4d-a328-b34ba566bd5d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they model semantics \n\nKeywords:\ncomputational sociolinguistics, dehumanization, lexical variation, language change, media, New York Times, LGBTQ\nWarning: this paper contains material that some may find offensive or upsetting.\... | [
"Yes"
] | 17,771 | qasper |
831730eb-4893-45c0-abf5-e6dbbc1ff72a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how did the authors translate the reviews to other languages?\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 ... | [
"Google translation API"
] | 3,545 | qasper |
835681d2-92dd-470f-8067-00cbbffb78c6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate their learned representations on downstream tasks?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic representation of ... | [
"No"
] | 2,510 | qasper |
a5203b2a-90de-43c7-9875-e2c7a193c1ca | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are there elements, other than pitch, that can potentially result in out of key converted singing?\n\nIntroduction\nSinging is an important way of human expression and the techniques of singing synthesis have broad applications in dif... | [
"Unanswerable"
] | 2,979 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.