uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
a2828188-0c0b-4ab1-8d31-8aee98cbf46d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Was PolyReponse evaluated against some baseline?\n\nIntroduction and Background\nTask-oriented dialogue systems are primarily designed to search and interact with large databases which contain information pertaining to a certain dialo...
[ "No" ]
3,846
qasper
aaf5589e-3c1c-41ec-bb88-efd3eb3c72c4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the three steps to feature elimination?\n\nIntroduction\nIn recent years, there has been a movement to leverage social medial data to detect, estimate, and track the change in prevalence of disease. For example, eating disord...
[ "reduced the dataset by eliminating features, apply feature selection to select highest ranked features to train and test the model and rank the performance of incrementally adding features." ]
2,801
qasper
aea7a309-36b1-4482-82d2-b982cebf9cd2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What details are given about the Twitter dataset?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by review...
[ "one of the Twitter datasets is about Turkish mobile network operators, there are positive, neutral and negative labels and provide the total amount plus the distribution of labels" ]
5,005
qasper
b3b8ea64-9d37-4d1f-8d37-e86aaea4b7c8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which matrix factorization methods do they use?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, and many ot...
[ "weighted factorization of a word-context co-occurrence matrix " ]
3,205
qasper
b6020af5-dff4-46bb-a3e0-150cdcd3cc22
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which words are used differently across ArXiv?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semantic structure in language....
[ "intelligence" ]
4,296
qasper
bcdb7e03-5368-4dd6-89f0-135f1501aa42
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does this approach compares to the state-of-the-art results on these tasks?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Wor...
[ "Unanswerable" ]
5,214
qasper
d5cee810-b273-4906-99f7-bf2d616a724f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which information about text structure is included in the corpus?\n\nIntroduction\nSimplified language is a variety of standard language characterized by reduced lexical and syntactic complexity, the addition of explanations for diffi...
[ "paragraph, lines, textspan element (paragraph segmentation, line segmentation, Information on physical page segmentation(for PDF only))" ]
3,694
qasper
e4b003a6-8a3c-4329-917a-1ca088696c83
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What activation function do they use in their model?\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 th...
[ "Activation function is hyperparameter. Possible values: relu, selu, tanh." ]
2,885
qasper
efc9ecaa-2d3f-400a-98e6-d481dce0475b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the other algorithms tested?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data sharing and processing capabiliti...
[ "NER model, CRF classifier trained with sklearn-crfsuite, classifier has been developed that consists of regular-expressions and dictionary look-up" ]
6,150
qasper
fc74fa8c-9491-4d16-a3a5-9bb8fbb55487
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset was used for training?\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 incre...
[ "Amazon reviews, Yelp restaurant reviews, restaurant reviews" ]
3,541
qasper
00dc037b-4044-423b-8702-bc91cea7ac07
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used?\n\nIntroduction\nBack to 42 BC, the philosopher Cicero has raised the issue that although there were many Oratory classes, there were none for Conversational skills BIBREF0 . He highlighted how important they w...
[ "a self-collected financial intents dataset in Portuguese" ]
17,788
qasper
0c8961e5-019c-4632-b337-14ef19703bf9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset did they use?\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 w...
[ " high-quality datasets from SemEval-2016 “Sentiment Analysis in Twitter” task" ]
3,586
qasper
15143287-3f06-4068-af98-c0a5ccab190b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What hierarchical modelling approach is used?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semantic structure in language. ...
[ "the group-specific embedding representations are tied through a global embedding" ]
4,293
qasper
152f33c3-8b6b-43c8-a69d-95a485b24ff7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are previous state of the art results?\n\nIntroduction\nNamed entity recognition (NER) is a challenging problem in Natural Language Processing, and often serves as an important step for many popular applications, such as informat...
[ "Overall F1 score:\n- He and Sun (2017) 58.23\n- Peng and Dredze (2017) 58.99\n- Xu et al. (2018) 59.11" ]
2,382
qasper
21424ed9-d4af-40a2-80ef-b7c620fdbf0e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baseline systems?\n\nIntroduction\nWe participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs: English INLINEFORM0 Czech, English INLINEFORM1 German, Englis...
[ " the dl4mt-tutorial" ]
2,989
qasper
2465a28b-cf39-4c37-b121-f186f9e25818
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets do they evaluate on?\n\nIntroduction\nData annotation is a major bottleneck for the application of supervised learning approaches to many problems. As a result, unsupervised methods that learn directly from unlabeled dat...
[ " Wall Street Journal (WSJ) portion of the Penn Treebank" ]
5,842
qasper
275f1e25-b11e-4494-b69a-0d9a50803539
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the accuracy merits of the approach demonstrated?\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 predetermi...
[ "significant improvements clearly demonstrate that our approach is effective at improving model performance" ]
6,676
qasper
2c888655-30e6-46e7-b2a7-a271aa12b619
[{"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 that tags the words before and after the pun as well as the pun words." ]
3,833
qasper
35f55fbf-86ac-48b0-a1fe-f371094414d4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"who transcribed the corpus?\n\nIntroduction\nNowadays deep learning techniques outperform the other conventional methods in most of the speech-related tasks. Training robust deep neural networks for each task depends on the availabili...
[ "Unanswerable" ]
5,097
qasper
512d2a10-7323-4460-a46f-ea580bcccfad
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is segmentation quality evaluated?\n\nIntroduction\nRhetorical Structure Theory (RST) BIBREF0 is a technique of Natural Language Processing (NLP), in which a document can be structured hierarchically according to its discourse. Th...
[ "we compare the Annodis segmentation with the automatically produced segmentation" ]
5,220
qasper
6bbfd62f-ea79-466b-b062-0aa4612e421a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What additional features and context are proposed?\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 . Ab...
[ "using tweets that one has replied or quoted to as contextual information" ]
2,919
qasper
71ba79fc-b062-4ae0-942a-7bf116cdf993
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What results do they achieve using their proposed approach?\n\nIntroduction\nNamed entity recognition (NER) BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 is the process by which we identify text spans which mention named entities, and to clas...
[ " total F-1 score on the OntoNotes dataset is 88%, total F-1 cross-validation score on the 112 class Wiki(gold) dataset is 53%" ]
3,158
qasper
78fc8190-57b4-4195-bd12-a6028fa46d65
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are used to represent the novelty of news articles to entity pages?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a r...
[ "KL-divergences of language models for the news article and the already added news references" ]
10,245
qasper
82b17d67-db30-4830-a2e0-727f92b36164
[{"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
83987343-9550-4edf-a5d3-e9063be76799
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use off-the-shelf NLP systems to build their assitant?\n\nIntroduction\nRobotic Process Automation (RPA) is a type of software bots that simulates hand-operated human activities like entering data into a system, registering in...
[ "No" ]
8,441
qasper
91d33bd9-6d32-4f9e-8bb9-94b979a63462
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the automatically constructed datasets subject to quality control?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly provided), ...
[ "No" ]
9,202
qasper
9a581518-948c-4c71-a9d2-a133d1d77c3e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how large is the vocabulary?\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 h...
[ "33,663" ]
4,424
qasper
a11187ce-d8f0-4e05-85e8-a2716c700d38
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the existing approaches?\n\nIntroduction\nUsers of photo-sharing websites such as Flickr often provide short textual descriptions in the form of tags to help others find the images. With the availability of GPS systems in cur...
[ "BOW-Tags, BOW-KL(Tags), BOW-All, GloVe" ]
6,181
qasper
a3d78f1e-81a6-4cc8-8229-e61c349b95db
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On top of BERT does the RNN layer work better or the transformer layer?\n\nIntroduction\nBidirectional Encoder Representations from Transformers (BERT) is a novel Transformer BIBREF0 model, which recently achieved state-of-the-art per...
[ "The transformer layer" ]
3,718
qasper
ad85b8d0-e8fc-4bfa-931b-a9e58c351d35
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics do they use?\n\nIntroduction\nSocial media is now becoming an important real-time information source, especially during natural disasters and emergencies. It is now very common for traditional news media to fre...
[ "BLEU-1, Meteor , Rouge-L " ]
4,645
qasper
ae9f37d1-ee50-410b-8af0-04848bdb071d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the interpretability merits of the approach demonstrated?\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 pr...
[ "By involving humans for post-hoc evaluation of model's interpretability" ]
6,677
qasper
aebbb248-998d-4687-ab56-a0b690144d18
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the decoder LSTMs all have the same weights?\n\nIntroduction\nOver the past few years, generating text from images and videos has gained a lot of attention in the Computer Vision and Natural Language Processing communities and seve...
[ "No" ]
1,777
qasper
b5fdf0ef-c9e1-46f4-9516-b419cf25c324
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are used to represent the salience and relative authority of entities?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into ...
[ "positional features, occurrence frequency, internal POS structure of the entity and the sentence it occurs in, relative entity frequency, centrality measures like PageRank " ]
10,245
qasper
b6f14deb-ec73-43de-83fb-1fbb8702995b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the disadvantages to clipping negative PMI?\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 vec...
[ "It may lead to poor rare word representations and word analogies." ]
3,415
qasper
c0964f4f-a80a-4578-b65a-4f564fd8c9d8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which other approaches do they compare their model with?\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 classif...
[ "Akbik et al. (2018), Link et al. (2012)" ]
3,158
qasper
c7810fce-9ed2-4f96-8a2c-fb792b821e06
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the source and target domains?\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...
[ "Book, electronics, beauty, music, IMDB, Yelp, cell phone, baby, DVDs, kitchen" ]
6,775
qasper
da6b1393-c5ba-45a2-bad0-77faf315b4d7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What can word subspace represent?\n\nIntroduction\nText classification has become an indispensable task due to the rapid growth in the number of texts in digital form available online. It aims to classify different texts, also called ...
[ "Word vectors, usually in the context of others within the same class" ]
7,837
qasper
e86e9f42-0870-4d92-80b7-5f115a433b38
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used?\n\nIntroduction\nRendering natural language descriptions from structured data is required in a wide variety of commercial applications such as generating descriptions of products, hotels, furniture, etc., from a ...
[ "WikiBio dataset, introduce two new biography datasets, one in French and one in German" ]
5,865
qasper
f2a5ec6c-49a1-491f-8efe-6a88f699036b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many question types do they find in the datasets analyzed?\n\nIntroduction\nQuestion answering (QA) has been a blooming research field for the last decade. Selection-based QA implies a family of tasks that find answer contexts fro...
[ "seven " ]
2,607
qasper
fdd5f266-d08a-4200-9a55-4cea01661e12
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big was the corpora they trained ELMo on?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems. The most well-known examples of ...
[ "2174000000, 989000000" ]
4,026
qasper
014d9dc7-8d29-4052-b634-9e40decab323
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What classification baselines are used for comparison?\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 GloveBI...
[ "VAE" ]
5,207
qasper
02f1a4a9-7184-46ef-8317-ec49508af5a8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why are current ELS's not sufficiently effective?\n\nIntroduction\nText summarization is a task to generate a shorter and concise version of a text while preserving the meaning of the original text. The task can be divided into two su...
[ "Linked entities may be ambiguous or too common" ]
5,268
qasper
0fecf5fd-8e41-4252-b73a-6629597d9b18
[{"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...
[ "user comments to newswire articles or to blog posts, forum posts, blog posts, newswire articles" ]
20,057
qasper
1ac9b66b-9d5b-4fae-901c-97a6ab6f697c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What different correlations result when using different variants of ROUGE scores?\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing for several decades. To compare and evalua...
[ "Using Pearson corelation measure, for example, ROUGE-1-P is 0.257 and ROUGE-3-F 0.878." ]
6,269
qasper
34d0d37c-88e1-4fd2-9014-5a6f914de603
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were the baselines?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribute similar one...
[ "bag-of-words (BOW), term frequency–inverse document frequency (TFIDF), neural-based word embedding, Logistic Regression (LR), Random Forest (RF), TextCNN BIBREF10 with initial word embedding as GloVe" ]
4,510
qasper
4b022167-edcb-44a1-98a7-2ec88b35b322
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What topics are included in the debate data?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/ Deep neural networks have...
[ "abortion (ABO), gay rights (GAY), Obama (OBA), and marijuana (MAR)" ]
5,898
qasper
54839653-d170-4598-8f1b-90ffcd6ef65d
[{"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...
[ "Best proposed model result vs best previous result:\nArxiv dataset: Rouge 1 (43.62 vs 42.81), Rouge L (29.30 vs 31.80), Meteor (21.78 vs 21.35)\nPubmed dataset: Rouge 1 (44.85 vs 44.29), Rouge L (31.48 vs 35.21), Meteor (20.83 vs 20.56)" ]
5,768
qasper
54f9552b-32cc-4be5-a28b-0edc1ac820f6
[{"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
57af6476-d70c-47f7-8883-4c12c3535426
[{"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...
[ "pivoting, pivoting$_{\\rm m}$" ]
5,433
qasper
5aab38e2-3bc3-480e-92e4-f3415601a8b7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How they utilize LDA and Gibbs sampling to evaluate ISWC and WWW publications?\n\nIntroduction\nToday, Internet is one of the widest available media worldwide. It has essentially become a huge hit of data that has the potential to ser...
[ "the LDA approaches to recommendation systems and given the importance of research, we have studied recent impressive articles on this subject and presented a taxonomy of recommendation systems based on LDA of the recent research, we evaluated ISWC and WWW conferences articles from DBLP website and used the Gibbs s...
6,380
qasper
6388092e-6fb6-4939-872e-1f93d9be1ea3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What learning models are used on the dataset?\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 . Abusive...
[ "Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Random Forests (RF), Gradient Boosted Trees (GBT), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN)" ]
2,920
qasper
658018ad-42fe-4dba-b0fe-77638dbb5956
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English datasets?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions. Since the answer to each question is ...
[ "Unanswerable" ]
5,688
qasper
6c4fb42f-6b10-4386-b08b-bfa469ff7eef
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their performance results?\n\nIntroduction\nCyberbullying has been defined by the National Crime Prevention Council as the use of the Internet, cell phones or other devices to send or post text or images intended to hurt or ...
[ "best model achieves 0.94 F1 score for Wikipedia and Twitter datasets and 0.95 F1 on Formspring dataset" ]
4,315
qasper
7ae74d07-ed98-440a-beb6-d532e7d1117e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used in this paper?\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 s...
[ "AMR Bank BIBREF10, CNN-Dailymail ( BIBREF11 BIBREF12 )" ]
5,731
qasper
7bf65dfb-e64d-4fd4-abe2-accec4fb991c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the meta knowledge specifically?\n\nIntroduction\nLearning the distributed representation for long spans of text from its constituents has been a key step for various natural language processing (NLP) tasks, such as text class...
[ "Unanswerable" ]
6,476
qasper
7f110de1-3be0-4b6c-9ff8-2fe5be3e895c
[{"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
8de72dd2-e0cd-447f-9cbb-473a140494c0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics were used for the summarization task?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their wor...
[ "ROUGE" ]
4,198
qasper
94ff86a3-14d1-40eb-bda2-5c9c6b0ebf9c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribute similar one...
[ "Friends, EmotionPush" ]
4,509
qasper
9a64ff9d-e059-4ce7-80e9-8b7df8d31873
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kinds of offensive content are explored?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the mos...
[ "Targeted Insult (TIN): Posts which contain an insult/threat to an individual, group, or others , Untargeted (UNT): Posts containing non-targeted profanity and swearing." ]
3,085
qasper
a7d3ecbb-a6e7-44ca-a7f7-544c1fd78c02
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use pretrained embeddings?\n\nIntroduction\nRendering natural language descriptions from structured data is required in a wide variety of commercial applications such as generating descriptions of products, hotels, furniture, ...
[ "Yes" ]
5,866
qasper
abe0f01b-11ba-4034-a7f2-81bea39b52f9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the characteristics of the accounts that spread fake news?\n\n10pt\n1.10pt\n[ Characterizing Political Fake News in Twitter by its Meta-DataJulio Amador Díaz LópezAxel Oehmichen Miguel Molina-Solana( j.amador, axelfrancois.oe...
[ "Accounts that spread fake news are mostly unverified, recently created and have on average high friends/followers ratio" ]
3,932
qasper
af76a0c6-1b29-4ff2-834b-a5b57734071a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data sources do they use for creating their dataset?\n\nIntroduction\nProgress in AI has been driven by, among other things, the development of challenging large-scale benchmarks like ImageNet BIBREF0 in computer vision, and SNLI...
[ "Wikipedia (of 250-600 characters) from the manually curated HotpotQA training set, formal spoken text (excerpted from court and presidential debate transcripts in the Manually Annotated Sub-Corpus (MASC) of the Open American National Corpus), causal or procedural text, which describes sequences of events or action...
6,706
qasper
b802aade-a999-4ad7-96ea-933266b5abbe
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the goal of investigating NLP gender bias specifically in the news broadcast domain and Anchor role?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous...
[ " broadcast recordings are also a valuable source of data for the speech processing community, recent works uncovering gender bias in several natural language processing (NLP) tools" ]
5,387
qasper
ba6dc47f-eab3-458e-82fd-75b1c10956d4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who were the human evaluators used?\n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2. However, complex neural summa...
[ "20 annotatos from author's institution" ]
5,011
qasper
beaf8700-5af2-4e13-88e1-e5fed0813bba
[{"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)...
[ "flexibility of neural networks, the generator is capable of learning complicated nonlinear distributions, supervision signal provided by the discriminator will help generator to capture the event-related patterns" ]
5,507
qasper
c33c627c-9e9f-404d-9937-77565c366505
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On which benchmarks they achieve the state of the art?\n\nIntroduction\nKnowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF...
[ "WebQSP, SimpleQuestions" ]
6,739
qasper
d2885b10-a9da-47c7-8f4f-ef9b095fedb5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which model architectures do they test their word importance approach on?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural differences, suc...
[ " Transformer BIBREF1 model and the conventional RNN-Search model BIBREF0" ]
5,822
qasper
d58fc467-fad5-4435-b509-1de1053d2f96
[{"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...
[ "French, English, Spanish, Italian, Portuguese, Hebrew, Arabic" ]
3,339
qasper
f6b870ac-980f-4659-97ba-1b308095dcf9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What domains are covered in the corpus?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automatic spe...
[ "No specific domain is covered in the corpus." ]
3,598
qasper
05d19205-e612-41a6-972c-dc95c3497bdd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets were used?\n\nIntroduction\nIn the field of natural language processing (NLP), the most prevalent neural approach to obtaining sentence representations is to use recurrent neural networks (RNNs), where words in a senten...
[ "SNLI BIBREF22 and MultiNLI BIBREF23, Quora Question Pairs dataset BIBREF24, Stanford Sentiment Treebank (SST) BIBREF25" ]
4,498
qasper
0da885dc-2d28-4c9b-b92d-9de4fdcd1c97
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the state of the art models?\n\nIntroduction\nSarcasm is defined as “a sharp, bitter, or cutting expression or remark; a bitter gibe or taunt”. As the fields of affective computing and sentiment analysis have gained increasin...
[ "BIBREF9 , BIBREF8 " ]
6,601
qasper
141e3953-c399-4d9e-b40f-4f291e26c637
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What Named Entity Recognition dataset is used?\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 mod...
[ "Groningen Meaning Bank (GMB)" ]
3,344
qasper
1a3bbd49-f350-463b-8c22-bf02be247423
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is Augmented LibriSpeech dataset?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automatic s...
[ "Unanswerable" ]
3,600
qasper
1f31ddd5-df43-4072-8e5d-4e51557285a6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the baseline?\n\nIntroduction\nTo appear in Proceedings of International Workshop on Health Intelligence (W3PHIAI) of the 34th AAAI Conference on Artificial Intelligence, 2020.\nPhysician burnout is a growing concern, estimate...
[ "QA PGNet and Multi-decoder QA PGNet" ]
6,487
qasper
2f6a8ce5-b633-4f1b-81c0-9272275d5655
[{"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
3ca5daf7-148f-4b29-9271-d22a4e552d03
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nConventional large-vocabulary continuous speech recognition (LVCSR) systems typically perform multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of ...
[ "WSJ" ]
3,652
qasper
41fdafb4-8514-4b5a-b765-bd36edfb16a6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what language does this paper focus on?\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...
[ "Simple English" ]
3,186
qasper
44634dcc-3d92-44b4-80d8-877fa6859ff8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does jiant involve datasets for the 50 NLU tasks?\n\nIntroduction\nThis paper introduces jiant, an open source toolkit that allows researchers to quickly experiment on a wide array of NLU tasks, using state-of-the-art NLP models, and ...
[ "Yes" ]
3,371
qasper
4746cfc4-606f-47ba-b1ba-b2693301d678
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nThe polarization of actors' expressed preferences is a fundamental concern for studies of legislatures, court systems, and international politics BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . Beca...
[ "corpus of state speeches delivered during the annual UN General Debate" ]
10,896
qasper
5bb75ba7-0db7-4e34-a277-f63bd2d238d1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is the dataset 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...
[ "212 accounts" ]
2,885
qasper
6c02f6d4-cf12-419a-9d92-f5e1f15a585f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what does the model learn in zero-shot setting?\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 large-scale ...
[ "we simply adopted the official training script of BERT, with default hyperparameters, to fine-tune each model until training loss converged" ]
3,416
qasper
6c4af68d-ec42-485b-8582-9e58d77e33a0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many sentences does the dataset contain?\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\" a...
[ "6946" ]
4,287
qasper
708c132a-a8af-4850-bdc3-ebb3078405a8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English datasets?\n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in particular tasks. Such features are often motivated by domain...
[ "Yes" ]
3,561
qasper
70ea2a77-2823-447d-9c90-65e8e49d343d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language(s) is/are represented in the dataset?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassment bec...
[ "english" ]
3,870
qasper
7c445f36-2ed1-48ff-8e59-e90a1b7a9e49
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many electrodes were used on the subject in EEG sessions?\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 , BIBREF...
[ "1913 signals" ]
3,285
qasper
87c490f7-b6b7-4b47-a5e7-820a7fcf672b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does the IPA label data after interacting with users?\n\nIntroduction\nRobotic Process Automation (RPA) is a type of software bots that simulates hand-operated human activities like entering data into a system, registering into ac...
[ "It defined a sequence labeling task to extract custom entities from user input and label the next action (out of 13 custom actions defined)." ]
8,436
qasper
90c15d3e-37a7-463c-9cce-3a007603d77c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset is used?\n\nIntroduction \nThe new generation of Neural Machine Translation (NMT) systems is known to be extremely data hungry BIBREF0 . Yet, most existing NMT training pipelines fail to fully take advantage of the very l...
[ "Europarl tests from 2006, 2007, 2008; WMT newstest 2014." ]
5,625
qasper
92fb22dd-2f10-451c-85a2-3457e280e727
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what standard dataset were used?\n\nIntroduction\nInformation extraction tasks have become very important not only in the Web, but also for in-house enterprise settings. One of the crucial steps towards understanding natural language ...
[ "GENIA Corpus BIBREF3, CoNLL2003 BIBREF14, KORE50 BIBREF21 , ACE2004 BIBREF22 and MSNBC" ]
4,083
qasper
a2a9581c-01c2-46aa-8bb3-c97d96b31d62
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"who transcribed the corpus?\n\nIntroduction\nNowadays deep learning techniques outperform the other conventional methods in most of the speech-related tasks. Training robust deep neural networks for each task depends on the availabili...
[ "Unanswerable" ]
5,097
qasper
b626bd63-6b0b-47a6-b040-cdfd47d44684
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used in evaluation?\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 generalise on dis...
[ "precision, recall , F1 score" ]
5,821
qasper
b8c06483-fd2f-4fe9-891a-41b547e9fe01
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What embedding techniques are explored in the paper?\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., INLINEFOR...
[ "integrated vector-res, vector-faith, Skip–gram, CBOW" ]
5,725
qasper
c7bc1e39-618a-4770-a0e1-d80589b347af
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"did they collect their own data?\n\nIntroduction\nNeural machine translation (NMT) BIBREF0 , BIBREF1 is widely applied for machine translation (MT) in recent years and focuses on popular language pairs such as English INLINEFORM0 Fren...
[ "No" ]
5,563
qasper
c9dfd277-0bc0-4407-845e-eb2ba06561d5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What background do they have?\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 rich online data with...
[ "Unanswerable" ]
10,567
qasper
cd43b795-4479-42f1-a8b5-a5ccb3ffed6d
[{"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...
[ "Sentence classification baselines: RNTN (Socher et al. 2013), AdaMC-RNTN (Dong et al. 2014), TE-RNTN (Qian et al. 2015), TBCNN (Mou et al. 2015), Tree-LSTM (Tai, Socher, and Manning 2015), AdaHT-LSTM-CM (Liu, Qiu, and Huang 2017), DC-TreeLSTM (Liu, Qiu, and Huang 2017), TE-LSTM (Huang, Qian, and Zhu 2017), BiConTr...
8,133
qasper
d3a7e36e-ab5b-4daf-903e-f308913e74f3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What biases are found in the dataset?\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to train and evaluate neural network models that gen...
[ "Ethnic bias" ]
2,927
qasper
d630d2b2-c6fe-4a0f-8283-0f04f66a2298
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which neural embedding model works better?\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 uti...
[ "the CRX model" ]
5,384
qasper
e67130f8-cc47-4272-ac4d-6754222be616
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the Random Kitchen Sink approach?\n\nIntroduction\nIn this digital era, online discussions and interactions has become a vital part of daily life of which a huge part is covered by social media platforms like twitter, facebook...
[ "explicitly maps data vectors to a space where linear separation is possible, RKS method provides an approximate kernel function via explicit mapping" ]
3,368
qasper
fead40ec-ac20-4ed2-b8fb-a827921c3ea1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of model is KAR?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions. Since the answer to each question is supposed to stem from ...
[ "Lexicon Embedding Layer, Context Embedding Layer, Coarse Memory Layer, Refined Memory Layer, Answer Span Prediction Layer" ]
5,687
qasper
0fdccbb1-cf9f-4691-9f11-e189f43f5404
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What manual Pyramid scores are used?\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing for several decades. To compare and evaluate the performance of different summarization...
[ "following the pyramid framework, we design an annotation scheme" ]
6,263
qasper
1b5a1436-4913-4bd4-82c2-3c6f50f248b3
[{"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...
[ " we use several of the MCQA baseline models first introduced in BIBREF0" ]
9,202
qasper