uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
797ef19d-4383-4604-af58-d69c4ffe5189
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the authors define a concept map?\n\nIntroduction\nMulti-document summarization (MDS), the transformation of a set of documents into a short text containing their most important aspects, is a long-studied problem in NLP. Genera...
[ "concept map BIBREF5 , a labeled graph showing concepts as nodes and relationships between them as edges" ]
5,675
qasper
7ef2fdaf-0b83-4f19-82f1-0cb94bdcc031
[{"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...
[ "Unanswerable" ]
3,415
qasper
89c312ce-57e0-4eab-b9f0-782feb1592ac
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of bioScope 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 tha...
[ "Unanswerable" ]
3,290
qasper
8fbe5b75-cb3f-4cb3-9f38-adc3966a4614
[{"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
d23684fc-7490-4576-894e-5afcd97f8c83
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the annotations automatic or manually created?\n\nIntroduction\nSeveral learner corpora have been compiled for English, such as the International Corpus of Learner English BIBREF0 . The importance of such resources has been increa...
[ "Automatic" ]
2,670
qasper
d5d87ab0-0616-4e19-935f-8ecd99878a8a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they improve on state-of-the-art semantic role induction?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, quest...
[ "Yes" ]
5,274
qasper
db25df92-8e52-46ee-9efc-d1c0b36026d3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What conclusions do the authors draw from their finding that the emotional appeal of ISIS and Catholic materials are similar?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Interne...
[ "By comparing scores for each word calculated using Depechemood dictionary and normalize emotional score for each article, they found Catholic and ISIS materials show similar scores" ]
4,682
qasper
dff5eebf-ab76-4ef2-acaa-4855d66232b0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the architecture of the span detector?\n\nBackground\nTeaching machine to read and comprehend a given passage/paragraph and answer its corresponding questions is a challenging task. It is also one of the long-term goals of nat...
[ "adopt a multi-turn answer module for the span detector BIBREF1" ]
2,440
qasper
e4583758-bdaf-47f7-a216-fbeefac02787
[{"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
ecb7dbeb-85b3-4ab5-805e-560a1a5ef960
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of inflections are considered?\n\nIntroduction\nThis paper describes our approach and results for Task 2 of the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection BIBREF0 . The task is to generate an i...
[ "Unanswerable" ]
3,048
qasper
fb5167ad-84f3-4415-8b13-321ddbe51f68
[{"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...
[ "adjectives are used to create “more narrow labels [or subtypes] for individuals who do not fit with general social category expectations”" ]
2,927
qasper
01b68a13-a384-45fe-9dad-fa2922ee5890
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different phenotypes are present in the dataset?\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 BIB...
[ "Thirteen different phenotypes are present in the dataset." ]
2,186
qasper
17472ea5-7138-4f60-bcb4-ba12d64b6c5d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages are evaluated?\n\nIntroduction\nThis paper describes our approach and results for Task 2 of the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection BIBREF0 . The task is to generate an inflected wo...
[ "Unanswerable" ]
3,045
qasper
2eef5c59-cad6-4ff7-b8e3-9964d01b1be5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nState-of-the-art automatic speech recognition (ASR) systems BIBREF0 have large model capacities and require significant quantities of training data to generalize. Labeling thousands of hours...
[ "190 hours ( INLINEFORM1 100K instances)" ]
2,231
qasper
52c568f4-9851-4089-93aa-179cdc61e102
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which basic neural architecture perform best by itself?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and aim individual user...
[ "BERT" ]
2,437
qasper
53bfc3e2-1893-490d-815f-b8002bda8136
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does this approach compare to other WSD approaches employing word embeddings?\n\nIntroduction\nLanguage modelling in its inception had one-hot vector encoding of words. However, it captures only alphabetic ordering but not the wor...
[ "GM$\\_$KL achieves better correlation than existing approaches for various metrics on SCWS dataset." ]
3,411
qasper
55efcc6e-0507-496f-ae5d-dd1ae2fa478d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset do they use?\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 train a lar...
[ "German newscrawl distributed by WMT'18 , English newscrawl data, WMT'18 English-German (en-de) news translation task , WMT'18 English-Turkish (en-tr) news task" ]
2,666
qasper
568949f7-439c-42ae-94cd-a02e643990d3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"HOw does the method perform compared with baselines?\n\nIntroduction\nThe Transformer architecture BIBREF0 for deep neural networks has quickly risen to prominence in NLP through its efficiency and performance, leading to improvements...
[ "On the datasets DE-EN, JA-EN, RO-EN, and EN-DE, the baseline achieves 29.79, 21.57, 32.70, and 26.02 BLEU score, respectively. The 1.5-entmax achieves 29.83, 22.13, 33.10, and 25.89 BLEU score, which is a difference of +0.04, +0.56, +0.40, and -0.13 BLEU score versus the baseline. The α-entmax achieves 29.90, 21...
7,822
qasper
5c399803-f1c8-498c-9df7-0382626cf76f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does PolyResponse architecture look like?\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 dialogue...
[ "Henderson:2017, MobileNet model" ]
3,845
qasper
6b35da9b-6247-4dfd-90d0-d2e31b608fc3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are sentences selected from the summary graph?\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 m...
[ " finding the important sentences from the story, extracting the key information from those sentences using their AMR graphs" ]
5,732
qasper
7cc82ba2-a1a4-4718-8528-2a2030a60ae1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What labels do they create on their dataset?\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 exchanged in such an...
[ "the time the patient has been experiencing the symptom, activities that trigger the symptom, the extent of seriousness, the frequency occurrence of the symptom, the location of symptom, 9 symptoms" ]
4,628
qasper
8083cb2c-ede6-42af-88c5-ee72fb94dbba
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who judged the irony accuracy, sentiment preservation and content preservation?\n\nIntroduction\nThe irony is a kind of figurative language, which is widely used on social media BIBREF0 . The irony is defined as a clash between the in...
[ "four annotators who are proficient in English" ]
6,084
qasper
837b7211-5404-42df-9884-47ce53fdb019
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What BERT models are 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 o...
[ "BERT-base, BERT-large, BERT-uncased, BERT-cased" ]
4,511
qasper
95576cdd-4347-4d73-9805-2ff0042d4a54
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much more does PARENT correlate with human judgements in comparison to other text generation metrics?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 ,...
[ "Their average correlation tops the best other model by 0.155 on WikiBio." ]
5,094
qasper
98b4abca-d547-4eb5-97de-09c919e52814
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is dataset for testing?\n\nIntroduction\nMedical text mining is an exciting area and is becoming attractive to natural language processing (NLP) researchers. Clinical notes are an example of text in the medical area that recen...
[ "30 terms, each term-sanse pair has around 15 samples for testing" ]
4,063
qasper
a1d125ce-c7a0-468a-afdd-e709473afb2b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\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 prominently, this...
[ "wFST" ]
4,275
qasper
a404ea3d-630e-42b8-81cf-3400f086d720
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Along which dimension do the semantically related words take larger values?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary buildin...
[ "dimension corresponding to the concept that the particular word belongs to" ]
8,087
qasper
a8b377e8-6d53-4204-ad9a-97596301589c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what previous RNN models do they compare with?\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 ar...
[ "Variational LSTM, CharCNN, Pointer Sentinel-LSTM, RHN, NAS Cell, SRU, QRNN, RAN, 4-layer skip-connection LSTM, AWD-LSTM, Quantized LSTM" ]
4,617
qasper
ae018748-f9aa-4e13-af43-c4df3f50c339
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages do they test on for the under-resourced scenario?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaigns...
[ "small portion of the large parallel corpus for English-German is used as a simulation" ]
5,752
qasper
b123df75-7a03-4387-83ea-7b052c5e3886
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the dataset annotated?\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 disorders in Spanish lang...
[ "The annotations are based on evidence of depression and further annotated by the depressive symptom if there is evidence of depression" ]
2,798
qasper
b4dfde36-9c85-4e19-8ddd-785db3593a66
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was annotation performed?\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 Pro...
[ "Experienced medical doctors used a linguistic annotation tool to annotate entities." ]
3,586
qasper
c0c91cd0-f7ee-4786-8183-8c87fb58167e
[{"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" ]
3,344
qasper
cd2cb8a2-a5e4-4208-b066-9b850d4c8d87
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the different components of the model trained? Is it trained end-to-end?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applie...
[ "the objective of our model is sum of the two processes, jointly trained using \"teacher-forcing\" algorithm, we feed the ground-truth summary to each decoder and minimize the objective, At test time, each time step we choose the predicted word by $\\hat{y} = argmax_{y^{\\prime }} P(y^{\\prime }|x)$ , use beam sear...
5,696
qasper
e5d392a2-3f6a-4049-b6cf-0e23ebef08df
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets did they use for evaluation?\n\nIntroduction\nBidirectional Encoder Representations from Transformers (BERT) is a novel Transformer BIBREF0 model, which recently achieved state-of-the-art performance in several language ...
[ "CSAT dataset, 20 newsgroups, Fisher Phase 1 corpus" ]
3,709
qasper
f4d081de-8886-4c47-8748-f4c6b92d5113
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they evaluate their resulting word embeddings?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, and m...
[ "We also evaluate all five models on downstream tasks from the VecEval suite BIBREF13 , using only the tasks for which training and evaluation data is freely available: chunking, sentiment and question classification, and natural language identification (NLI). The default settings from the suite are used, but we ru...
3,205
qasper
f51f0d39-f54b-45f0-a202-cd51bc541852
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which stock market sector achieved the best performance?\n\nIntroduction\nNatural Language Processing (NLP) has increasingly attracted the attention of the financial community. This trend can be explained by at least three major facto...
[ "Energy with accuracy of 0.538" ]
15,739
qasper
069c50ee-fd58-4c33-9908-eb961b715c64
[{"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 ...
[ "No-Answer Baseline (NA), Word Count Baseline, Human Performance" ]
5,283
qasper
152b9872-de0e-41cd-904e-96ec4979e8b7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why are statistics from finite corpora unreliable?\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 vecto...
[ "$\\mathit {PMI}(w,c)$ goes to negative infinity when the word-context pair $(w,c)$ does not appear in the training corpus" ]
3,414
qasper
1abe1061-aca6-47a7-994c-b83219c8b9b1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many labels do the datasets have?\n\nIntroduction\nIn practice, it is often difficult and costly to annotate sufficient training data for diverse application domains on-the-fly. We may have sufficient labeled data in an existing d...
[ "Book, Electronics, Beauty and Music each have 6000, IMDB 84919, Yelp 231163, Cell Phone 194792 and Baby 160792 labeled data." ]
6,775
qasper
366f0093-6d81-4ca9-a0ac-8ad99700b748
[{"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...
[ "Document to Vector (Doc2Vec)" ]
11,281
qasper
3b03e134-2770-479b-b9cc-63535f27aeaf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is diversity measured?\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 hav...
[ " the average dissimilarity of all pairs of tags in the list of recommended tags" ]
4,423
qasper
401b4ad8-3d2a-4752-8018-f69eb47314f8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline used?\n\nIntroduction\nWriting errors can occur in many different forms – from relatively simple punctuation and determiner errors, to mistakes including word tense and form, incorrect collocations and erroneous ...
[ "error detection system by Rei2016" ]
2,710
qasper
47facb7d-384f-4777-9970-d86b096c2f31
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What boundary assembling method is used?\n\nIntroduction\nNamed entity recognition (NER) is a challenging problem in Natural Language Processing, and often serves as an important step for many popular applications, such as information...
[ "This motivates us to carry out a backward greedy search over each sentence's label sequence to identify word boundaries. If two words segmented in a sentence are identified as nouns, and one word is immediately before the other, we assemble their boundaries, creating a new word candidate for entity recognition." ]
2,380
qasper
559fff51-e4e5-4ac0-beaa-f6f8e6169d2c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how was the speech collected?\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 availabi...
[ "Android application" ]
5,097
qasper
567c2512-c693-406f-93c7-afe6a426edce
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the model transferred to other languages?\n\nIntroduction\nPre-trained models BIBREF0, BIBREF1 have received much of attention recently thanks to their impressive results in many down stream NLP tasks. Additionally, multilingua...
[ "Build a bilingual language model, learn the target language specific parameters starting from a pretrained English LM , fine-tune both English and target model to obtain the bilingual LM." ]
5,302
qasper
5942efe5-1e02-4ca7-81b1-92d1519dbf80
[{"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...
[ "seq2seq model with global attention gives the best results with an average target BLEU score of 29.65" ]
2,143
qasper
673dbe5b-e471-44d0-aeb1-e80b75e31c9d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What accuracy does the proposed system achieve?\n\nIntroduction\nThere has been significant progress on Named Entity Recognition (NER) in recent years using models based on machine learning algorithms BIBREF0 , BIBREF1 , BIBREF2 . As ...
[ "F1 of 85.99 on the DL-PS dataset (dialog domain); 75.15 on EC-MT and 71.53 on EC-UQ (e-commerce domain)" ]
8,638
qasper
69dfee18-9c7b-4a47-89b3-a172867595fe
[{"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...
[ "They compare to Akbik et al. (2018) and Link et al. (2012)." ]
3,158
qasper
80e321b5-74f7-4609-9dc1-82b8473fb7f4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What state-of-the-art deep neural network is used?\n\nIntroduction\nNamed entity recognition (NER) is a challenging problem in Natural Language Processing, and often serves as an important step for many popular applications, such as i...
[ "LSTM model" ]
2,384
qasper
86641d80-cc3d-4f48-87e4-660adce957a4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for the STS tasks?\n\nIntroduction\nIn this publication, we present Sentence-BERT (SBERT), a modification of the BERT network using siamese and triplet networks that is able to derive semantically meaningful sent...
[ "Spearman's rank correlation between the cosine-similarity of the sentence embeddings and the gold labels" ]
5,618
qasper
86a4a1ea-4ce2-4556-af4f-7a8b6bd72ac0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the difficulties in modelling the ironic pattern?\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 a s...
[ "ironies are often obscure and hard to understand" ]
6,082
qasper
9c12fe9a-6d00-432f-bb65-b20cfe084c6a
[{"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
aa31deb1-4abf-4867-a2b2-4e5918d2f63a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who were the experts used for annotation?\n\nIntroduction\nPrivacy policies are the documents which disclose the ways in which a company gathers, uses, shares and manages a user's data. As legal documents, they function using the prin...
[ "Yes" ]
5,279
qasper
ac8d238b-7ab3-4e1c-ba70-3033df756a0d
[{"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 BIBREF0, KEA BIBREF4 and Maui BIBREF8, CopyRNN*" ]
6,244
qasper
b0e04bdb-df15-48e9-a1d4-64a51ff9ee16
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Overall, does having parallel data improve semantic role induction across multiple languages?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability...
[ "No" ]
5,276
qasper
bd5165fb-23fa-443e-8a19-e6381895bb1e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\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 language...
[ "Unanswerable" ]
8,579
qasper
c02784e6-faec-409e-a1dc-3285c29be3fb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many GPUs are used for the training of SBERT?\n\nIntroduction\nIn this publication, we present Sentence-BERT (SBERT), a modification of the BERT network using siamese and triplet networks that is able to derive semantically meanin...
[ "Unanswerable" ]
5,620
qasper
c0bf27ed-f2b5-4cad-83fb-03d774e6feb8
[{"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. BIBREF21, paper by BIBREF33 in which they used maximum entropy classifier with bag of words model to classify various emotional datasets" ]
3,187
qasper
c1c02aa5-9b22-4b88-9305-965e509ea71a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their framework always generate purely attention-based models?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaig...
[ "Unanswerable" ]
5,749
qasper
cd9779e6-9e7d-415c-acc1-eeaf3b06407b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different characters were in dataset?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BIBREF0. This is largely due to in...
[ "45,821 characters" ]
7,237
qasper
d56cbb2e-72af-4605-b79b-c64ee489c8fc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the strong baseline?\n\nIntroduction\nTable-to-text generation is an important and challenging task in natural language processing, which aims to produce the summarization of numerical table BIBREF0, BIBREF1. The related metho...
[ "delayed copy model (DEL), template system (TEM), conditional copy (CC), NCP+CC (NCP)" ]
6,980
qasper
dfb63eae-5e7e-47e9-b503-80640b28a2d6
[{"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...
[ "versions of LiLi" ]
8,578
qasper
f7f29ae0-b903-4ebc-a53c-face074e83a8
[{"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 ...
[ "The encoder takes the images in order, one at every timestep $t$ . At time $t=5$ , we obtain the context vector through $h_e^{(t)}$ (represented by $\\mathbf {Z}$ ). This vector is used to initialize each decoder's hidden state while the first input to each decoder is its corresponding image embedding $e(I_i)$ . E...
1,775
qasper
04167825-f6f5-48a5-9f13-a3d47b3433bb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is this hashtag prediction task an established task, or something new?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low fr...
[ "established task" ]
3,482
qasper
190a373e-c6f4-416f-9f9e-e3066364deb6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the experiments focus on a specific domain?\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 divers...
[ "No" ]
2,008
qasper
1dffcdeb-0085-4662-9f8d-7705cceea918
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What news article sources are used?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages for the Eng...
[ "Unanswerable" ]
10,237
qasper
2218574d-fd52-4f58-860a-b00a6be83cab
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which collections of web documents are included in the corpus?\n\nIntroduction\nMulti-document summarization (MDS), the transformation of a set of documents into a short text containing their most important aspects, is a long-studied ...
[ "DIP corpus BIBREF37" ]
5,677
qasper
3814b52e-28eb-4a0e-8da3-6cefb9070042
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments are proposed to test that upper layers produce context-specific embeddings?\n\nIntroduction\nThe application of deep learning methods to NLP is made possible by representing words as vectors in a low-dimensional conti...
[ "They measure self-similarity, intra-sentence similarity and maximum explainable variance of the embeddings in the upper layers." ]
6,140
qasper
38a9acf6-00b0-4ba1-bbe8-58042d6008fa
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which stock market sector achieved the best performance?\n\nIntroduction\nNatural Language Processing (NLP) has increasingly attracted the attention of the financial community. This trend can be explained by at least three major facto...
[ "Energy" ]
15,739
qasper
3996f531-de1c-4cdf-a42f-16504554a430
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what bias evaluation metrics are used?\n\nIntroduction\nNatural Language Processing (NLP) models are shown to capture unwanted biases and stereotypes found in the training data which raise concerns about socioeconomic, ethnic and gend...
[ "gender bias, normalized version of INLINEFORM0, ratio of occurrence of male and female words in the model generated text, Causal occupation bias conditioned on occupation, causal occupation bias conditioned on gender, INLINEFORM1" ]
3,224
qasper
416fd681-5aba-43cf-9a37-1b96d2e92d11
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the training data translated?\n\nIntroduction\nUnderstanding the emotions expressed in a text or message is of high relevance nowadays. Companies are interested in this to get an understanding of the sentiment of their current...
[ "using the machine translation platform Apertium " ]
3,099
qasper
502d0356-eda2-4223-b0c7-6136750609a8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation metrics did they use?\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 p...
[ "BLEU, FKGL, SARI, Simplicity" ]
3,185
qasper
55630021-578b-4e30-9a2e-2bcf21dc5cc3
[{"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...
[ "car " ]
2,205
qasper
5c03b5c0-ea14-43b3-8bd6-e77956917f20
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many articles are in the dataset?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nRecent years have seen a surge ...
[ "244 " ]
2,275
qasper
5c96692d-24a5-4215-8654-b7ce5f560aab
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does the \"sensitivity\" quantity denote?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the data distribution. Even w...
[ "the number of distinct word recognition outputs that an attacker can induce, not just the number of words on which the model is “fooled”" ]
5,904
qasper
831111c3-9275-4225-a9c4-d9ac020cb806
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What previous methods is their model compared to?\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 classificat...
[ "bag-of-words model, CNN" ]
8,029
qasper
85dd3264-6e3f-45cd-b043-d3262bcca2be
[{"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...
[ "Total dataset size: 171 account (522967 tweets)" ]
2,885
qasper
9a834ef1-c1d3-421b-8d4f-1811fcdadb8c
[{"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
b56446db-11cd-4dec-9cc5-62bea0aad76e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was this data collected?\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 can prov...
[ "The crowdsourcing platform CrowdFlower was used to obtain natural dialog data that prompted the user to paraphrase, explain, and/or answer a question from a Simple questions BIBREF7 dataset. The CrowdFlower users were restricted to English-speaking countries to avoid dialogs with poor English." ]
3,237
qasper
c7383c50-f2a6-47c2-aaaa-b18ec0d53a8b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the word-level baseline?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low frequency. Estimating the statistical pr...
[ "The encoder is essentially the same as tweet2vec, with the input as words instead of characters." ]
3,476
qasper
c989e93e-e04a-4874-acd5-99f45aa67ddd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper explore extraction from electronic health records?\n\nIntroduction\nThe explosion of available scientific articles in the Biomedical domain has led to the rise of Biomedical Information Extraction (BioIE). BioIE systems...
[ "Yes" ]
3,933
qasper
da1f628c-f066-46bf-ab41-36a38a1a08d0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they measure which words are under-translated by NMT models?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural differences, such as E...
[ "They measured the under-translated words with low word importance score as calculated by Attribution.\nmethod" ]
5,825
qasper
dcb311f2-89e5-438f-9395-a63d979ffdd3
[{"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...
[ "from 3rd to 9th grade science questions collected from 12 US states" ]
8,026
qasper
ef3427d9-11cc-499a-823e-141803512efb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What models are used in the experiment?\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 comm...
[ "linear SVM, bidirectional Long Short-Term-Memory (BiLSTM), Convolutional Neural Network (CNN)" ]
3,085
qasper
efc16d3b-8f48-4b64-be5a-bf64ab8f7c20
[{"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...
[ "we also account for political biases inherent to different news sources, referring to the procedure proposed in BIBREF2 to label different outlets. Overall we show that we are able to classify credible vs non-credible diffusion networks (and consequently news articles) with high accuracy (AUROC up to 94%), even wh...
6,633
qasper
f1b43e3a-ee6d-44fb-adc9-b3b594bae183
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the five different binary classification tasks?\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 . I...
[ " presence/absence of consonants, phonemic nasal, bilabial, high-front vowels and high-back vowels." ]
3,282
qasper
f4fa3050-c07e-4c75-adda-21c77eb85e5c
[{"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...
[ "paragraphs, lines, Information on physical page segmentation (for PDFs only), paragraph segmentation, and line segmentation" ]
3,694
qasper
fdf1c277-925c-4ac5-9dd3-a762934c4fd8
[{"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...
[ "By using topic modeling and unsupervised emotion detection on ISIS materials and articles from Catholic women forum" ]
4,679
qasper
0143a66d-38d0-4801-a3e4-e3c5d185befc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much did they improve?\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 thi...
[ "They decrease MAE in 0.34" ]
3,587
qasper
075c2244-084e-48d5-9ff9-2c5585ff2fdf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language are the reviews in?\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...
[ "Unanswerable" ]
4,701
qasper
0da5cd21-bd8d-4694-abac-0e27e056df98
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What novel PMI variants are introduced?\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 vectors can be l...
[ "clipped $\\mathit {PMI}$, $\\mathit {NNEGPMI}$" ]
3,413
qasper
1d684d5d-e86c-4b9c-9f33-8d3175ab767e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the student reflection data very different from the newspaper data? \n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, B...
[ "Yes" ]
5,016
qasper
21516f9d-7639-4df0-b946-84371cbb122e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which 7 Indian languages do they experiment with?\n\nINTRODUCTION\nThe idea of language identification is to classify a given audio signal into a particular class using a classification algorithm. Commonly language identification task...
[ "Hindi, English, Kannada, Telugu, Assamese, Bengali and Malayalam" ]
3,270
qasper
2ca0ce01-a680-4c73-bb64-8d729888532e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What pooling function is used?\n\nIntroduction\nRecurrent neural networks (RNNs), including gated variants such as the long short-term memory (LSTM) BIBREF0 have become the standard model architecture for deep learning approaches to s...
[ " f-pooling, fo-pooling, and ifo-pooling " ]
4,696
qasper
332f07d7-d00b-4f73-8f7d-0636e3c612dc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of latent context is used to predict instructor intervention?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quality education from reputed universi...
[ "the series of posts that trigger an intervention" ]
4,780
qasper
4084b40f-10f0-4b63-90ba-4ef4f1ea34cd
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of BERT on the task?\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 cap...
[ "F1 scores are:\nHUBES-PHI: Detection(0.965), Classification relaxed (0.95), Classification strict (0.937)\nMedoccan: Detection(0.972), Classification (0.967)" ]
6,154
qasper
427849b2-2d18-4708-893e-be28494cd692
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which languages are explored in this paper?\n\nIntroduction\nWriting errors can occur in many different forms – from relatively simple punctuation and determiner errors, to mistakes including word tense and form, incorrect collocation...
[ "English " ]
2,712
qasper
44773f12-f7ab-40f9-a64c-521f4555fd8c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"For how many probe tasks the shallow-syntax-aware contextual embedding perform better than ELMo’s embedding?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextu...
[ "performance of baseline ELMo-transformer and mSynC are similar, with mSynC doing slightly worse on 7 out of 9 tasks" ]
3,693
qasper
506fbe77-aa0b-4119-9d19-2507e7130622
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where is a question generation model used?\n\nIntroduction\nIn recent years, there has been an increasing interest in Machine reading comprehension (MRC), which plays a vital role in the assessment of how well a machine could understa...
[ "framework consisting of both a question answering model and a question generation model" ]
5,578
qasper
59b75df9-9918-4dbf-8a6b-4afa27d32a53
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language model architectures are used?\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...
[ "bi-directional language model to augment the sequence to sequence encoder , uni-directional model to augment the decoder" ]
2,667
qasper