uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
eb3b84c3-8850-439f-a8bc-2c37e6d8e09c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How long are the essays on average?\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 increasingly recogniz...
[ "Most texts, however, range roughly from 150 to 250 tokens." ]
2,670
qasper
f743972e-ef1e-44b0-9bd2-45d697f2a87f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which two news domains are country-independent?\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...
[ "mainstream news and disinformation" ]
6,628
qasper
fd1354e7-b772-4b63-aaff-7b1ff512109f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of social media did they consider?\n\nIntroduction\nExplanations of happenings in one's life, causal explanations, are an important topic of study in social, psychological, economic, and behavioral sciences. For example, ps...
[ "Facebook status update messages" ]
5,201
qasper
067ed2ed-f925-4413-8373-e4ed111e9a6a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the baseline?\n\nIntroduction and Background\nThe task of interpreting and following natural language (NL) navigation instructions involves interleaving different signals, at the very least the linguistic utterance and the rep...
[ "NO-MOVE: the only position considered is the starting point, RANDOM: As in BIBREF4, turn to a randomly selected heading, then execute a number of *WALK actions of an average route, JUMP: at each sentence, extract entities from the map and move between them in the order they appear" ]
3,009
qasper
0928d84a-8c0d-48e0-80cb-27fb0136e787
[{"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...
[ "1. Loaded language, 2. Name calling or labeling, 3. Repetition, 4. Exaggeration or minimization, 5. Doubt, 6. Appeal to fear/prejudice, 7. Flag-waving, 8. Causal oversimplification, 9. Slogans, 10. Appeal to authority, 11. Black-and-white fallacy, dictatorship, 12. Thought-terminating cliché, 13. Whataboutism, 14....
4,231
qasper
24666da1-5c8c-4fa6-aae5-4802399c9326
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big are significant improvements?\n\nIntroduction\nQuestion Generation (QG) is the task of automatically creating questions from a range of inputs, such as natural language text BIBREF0, knowledge base BIBREF1 and image BIBREF2. Q...
[ "Metrics show better results on all metrics compared to baseline except Bleu1 on Zhou split (worse by 0.11 compared to baseline). Bleu1 score on DuSplit is 45.66 compared to best baseline 43.47, other metrics on average by 1" ]
5,603
qasper
45362302-d634-4965-8665-cb60e99c7a5e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the previously reported results?\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 syste...
[ "Figures FIGREF1 and FIGREF1 contain a summary of the papers addressing speculation detection and scope resolution" ]
3,288
qasper
547139fa-3656-44cd-8478-60632a4aa956
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How long of dialog history is captured?\n\nIntroduction\nLanguage model plays an important role in many natural language processing systems, such as in automatic speech recognition BIBREF0 , BIBREF1 and machine translation systems BIB...
[ "160" ]
3,782
qasper
60844688-a75d-41ac-b4ba-35630d2f5fa0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did the authors find ironic data on twitter?\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 sentence an...
[ "They developed a classifier to find ironic sentences in twitter data" ]
6,082
qasper
61c6aa52-29f1-4758-a293-5589cbc4061a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what data simulation techniques were introduced?\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 t...
[ "copy, copy-marked, copy-dummies" ]
5,627
qasper
663d9a7d-2f0f-4567-afe3-6af6e34c8d1c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the source of their dataset?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"ORGANIZATION\" and other...
[ "daily newspaper of the year 2015-2016" ]
4,287
qasper
6b3c5a18-37fe-40cc-8d98-c7c5881016b1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which models are used to solve NER for Nepali?\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" ]
4,291
qasper
702f314d-c40a-4ea8-a5aa-09159399b654
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what 8 languages is PolyResponse engine used for restourant search and booking system?\n\nIntroduction and Background\nTask-oriented dialogue systems are primarily designed to search and interact with large databases which contain ...
[ "English, German, Spanish, Mandarin, Polish, Russian, Korean and Serbian" ]
3,856
qasper
75e29dc8-4e16-4fc9-8811-c14d8564cdf3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the industry classes defined in this paper?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who thei...
[ "Technology, Religion, Fashion, Publishing, Sports coach, Real Estate, Law, Environment, Tourism, Construction, Museums, Banking, Security, Automotive." ]
5,300
qasper
7707fec6-52d2-4efc-aa8a-44d6cff91f88
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the source of the news articles?\n\nIntroduction\nThe distribution of textual content is typically very fast and catches user attention for only a short period of time BIBREF0 . For this reason, proper wording of the article t...
[ "main news channels, such as Yahoo News, The Guardian or The Washington Post" ]
3,080
qasper
79155d3c-0d75-4645-83a3-fa1c7d71c23f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is te core component for KBQA?\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 qu...
[ "hierarchical matching between questions and relations with residual learning" ]
6,737
qasper
792747a4-bc4d-47f6-a2fc-3d337093307a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why are prior knowledge distillation techniques models are ineffective in producing student models with vocabularies different from the original teacher models? \n\nIntroduction\nRecently, contextual-aware language models such as ELM...
[ "While there has been existing work on reducing NLP model vocabulary sizes BIBREF15, distillation techniques cannot utilize these, since they require the student and teacher models to share the same vocabulary and output space. This profoundly limits their potential to further reduce model sizes." ]
4,896
qasper
7bce413c-8cc2-4c3b-8418-535ecd1041d5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline system is proposed?\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. Generated sum...
[ "Answer with content missing: (Baseline Method section) We implemented a simple approach inspired by previous work on concept map generation and keyphrase extraction." ]
5,672
qasper
7de53e1f-f5fd-49b6-ba74-71d8bbcc7b96
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the two new strategies?\n\nIntroduction and Background\nMany reinforcement learning algorithms are designed for relatively small discrete or continuous action spaces and so have trouble scaling. Text-adventure games—or intera...
[ "a method that detects bottlenecks in text-games using the overall reward gained and the knowledge graph state, to leverage knowledge graphs to improve existing exploration algorithms for dealing with combinatorial action-space" ]
3,183
qasper
88a58efd-fa6a-4627-9edf-ea2a65d3530b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is it possible to convert a cloze-style questions to a naturally-looking questions?\n\nIntroduction\nDeep learning systems have shown a lot of promise for extractive Question Answering (QA), with performance comparable to humans when ...
[ "Unanswerable" ]
3,900
qasper
89d9dd68-b707-45a1-b52e-5c9771088ed6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the architecture of the model?\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 ...
[ "one-layer CNN structure from previous works BIBREF22 , BIBREF4" ]
6,775
qasper
9136fffb-1753-40eb-9803-ae5ee11cfe49
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they only experiment with one language pair?\n\nIntroduction\nReordering in machine translation (MT) is a crucial process to get the correct translation output word order given an input source sentence, as word order reflects mean...
[ "Yes" ]
6,022
qasper
9b5141f6-cc4a-4664-ad55-8f1623852f49
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the state of the art on WSJ?\n\nIntroduction\nRecent work on convolutional neural network architectures showed that they are competitive with recurrent architectures even on tasks where modeling long-range dependencies is crit...
[ "CNN-DNN-BLSTM-HMM" ]
2,774
qasper
9c76293b-de05-45f6-aaf6-a3f35266eee3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the distinctive characteristics of how Arabic speakers use offensive language?\n\nIntroduction\nDisclaimer: Due to the nature of the paper, some examples contain highly offensive language and hate speech. They don't reflect t...
[ "Direct name calling, Simile and metaphor, Indirect speech, Wishing Evil, Name alteration, Societal stratification, Immoral behavior, Sexually related" ]
7,109
qasper
9c998b3d-d9db-496d-94d4-020881df1a45
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What user variations have been tested?\n\nIntroduction\nSuppose a user wants to write a sentence “I will be 10 minutes late.” Ideally, she would type just a few keywords such as “10 minutes late” and an autocomplete system would be ab...
[ "Unanswerable" ]
2,582
qasper
a4ea73a0-7166-4735-962d-0845dac3ba6f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of issues (that are not on the forefront of computational text analysis) do they tackle?\n\nIntroduction\nIn June 2015, the operators of the online discussion site Reddit banned several communities under new anti-harassment ...
[ "identifying the questions we wish to explore, Can text analysis provide a new perspective on a “big question” that has been attracting interest for years?, How can we explain what we observe?, hope to connect to multiple disciplines" ]
10,581
qasper
bc0764af-83ed-457f-95fc-2541b924279c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which sports clubs are the targets?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually d...
[ "Galatasaray , Fenerbahçe " ]
2,821
qasper
c3b2afdb-d06f-4e70-aaaf-97c5d2785650
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper report the performance of a baseline model on South African languages LID?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipeline...
[ "Yes" ]
2,619
qasper
d5f8e1e2-c291-4628-9d90-bc2f22e6b45f
[{"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
e4e4f8d6-470e-4b38-b660-9fecb5ac113b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a semicharacter architecture?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the data distribution. Even when the p...
[ "processes a sentence of words with misspelled characters, predicting the correct words at each step" ]
5,903
qasper
ebebde64-43a6-4bbc-beae-a639f6a550ab
[{"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
f04c4939-d353-47a3-ace0-6f561124d0a9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the keyword specific expectation elicited from the crowd?\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 pre...
[ "workers are first asked to find those microposts where the model predictions are deemed correct, asked to find the keyword that best indicates the class of the microposts" ]
6,678
qasper
f658265e-4fc4-4adf-9809-29a18dec2c05
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the system tested on low-resource 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, multilingual...
[ "Yes" ]
5,302
qasper
102587c6-39ad-485d-ad53-36948baf57c1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of system does the baseline classification use?\n\nIntroduction\n“Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various lan...
[ "support vector machine BIBREF18 , random forest, extra tree and naive bayes classifier BIBREF19" ]
3,611
qasper
10728eca-19d4-4ba4-b5b3-66d8f114cf18
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used for this study?\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 Spani...
[ "BIBREF12 , BIBREF13" ]
2,800
qasper
1587f7c6-7085-45fb-a52b-fb55ce0e519d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the previous state-of-the-art in summarization?\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 . ...
[ "BIBREF26 " ]
2,672
qasper
21b4018a-bf99-4692-8359-48e04e458eb2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was their highest recall score?\n\nIntroduction\nBioASQ is a biomedical document classification, document retrieval, and question answering competition, currently in its seventh year. We provide an overview of our submissions to ...
[ "0.7033" ]
9,716
qasper
26119d4b-9ec4-46c7-8827-8f488f75067a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they analyze contextual similaries across datasets?\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 from la...
[ "They compare the tasks that the datasets are suitable for, average number of answer candidates per question, number of token types, average answer candidate lengths, average question lengths, question-answer word overlap." ]
2,605
qasper
32c05ff1-f806-4f02-b594-5e576d22fb22
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the baselines?\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 sentenc...
[ "(i) models that use plain stacked LSTMs, (ii) models with different INLINEFORM0, (iii) models without INLINEFORM1, (iv) models that integrate lower contexts via peephole connections" ]
4,499
qasper
37cb6d67-263f-4808-9faf-ae6b0cda4792
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do their models decide how much improtance to give to the output words?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural differences, s...
[ "Given the contribution matrix, we can obtain the word importance of each input word to the entire output sentence. " ]
5,827
qasper
4a4f54ae-8a9c-4938-8d1e-11c34af05059
[{"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
4c76a05c-8499-4954-ae23-ea8a9504ccc8
[{"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 ...
[ "Domain experts and fellow researchers can provide feedback on questions and help with dynamically revising them., connect to multiple disciplines, dual use" ]
10,570
qasper
5034bdac-e486-4857-adf5-9fbbd5af78f2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset was 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 gender discriminatio...
[ "Daily Mail news articles released by BIBREF9 " ]
3,222
qasper
54bc5e00-0b9b-4915-964c-42730f0f7241
[{"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...
[ "non-targeted profanity and swearing, targeted insults such as cyberbullying, offensive content related to ethnicity, gender or sexual orientation, political affiliation, religious belief, and anything belonging to hate speech" ]
3,085
qasper
55f928ae-4956-4d2a-858d-71807602499a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the template-based model realistic? \n\nIntroduction\nRecently, with the emergence of neural seq2seq models, abstractive summarization methods have seen great performance strides BIBREF0, BIBREF1, BIBREF2. However, complex neural ...
[ "Yes" ]
5,011
qasper
6892e32f-c90e-4ff4-90cd-fa4ef829f847
[{"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 ...
[ "The GENIA Corpus , CoNLL2003" ]
4,083
qasper
6bce820b-34c3-4582-96e3-919632d0c275
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baselines?\n\nIntroduction\nCLIR systems retrieve documents written in a language that is different from search query language BIBREF0 . The primary objective of CLIR is to translate or project a query into the language o...
[ "the baseline transformer BIBREF8" ]
2,858
qasper
7bc6f40a-336a-4bc8-bfda-b8a730cb76d2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which datasets did they experiment with?\n\nIntroduction\nPart-of-speech tagging is now a classic task in natural language processing, for which many systems have been developed or adapted for a large variety of languages. Its aim is ...
[ "Universal Dependencies v1.2 treebanks BIBREF21 , hereafter UD1.2" ]
3,760
qasper
8a693eb5-a3f7-436b-b2c3-bd6769be014e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used in evaluation?\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 in...
[ "SemEval-2016 Challenge Task 5 BIBREF27 , BIBREF28" ]
3,541
qasper
9144e614-63e6-4f44-a455-5e338409167b
[{"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), Macro-averaged F1 scores (F1)" ]
3,112
qasper
91e8f10e-5010-406b-8d2b-b989d9732531
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which benchmark datasets are used?\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 increasing p...
[ "Semeval 2014 BIBREF34 Twitter Sentiment Analysis Dataset , dataset was created by BIBREF8, English dataset from BIBREF8, dataset from The Sarcasm Detector" ]
6,598
qasper
93fbfadc-1e20-4019-9f2e-37c9ffcb667f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What state-of-the-art results are achieved?\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 m...
[ "F1 score of 92.19 on homographic pun detection, 80.19 on homographic pun location, 89.76 on heterographic pun detection." ]
3,835
qasper
98ba586e-f042-419d-a77f-0dae2ff56ad1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the Airbnb?\n\nIntroduction\nThe development of online peer-to-peer markets in the 1990s, galvanized by the launch of sites like eBay, fundamentally shifted the way buyers and sellers could connect [4]. These new m...
[ "roughly 40,000 Manhattan listings" ]
3,507
qasper
ade87881-bd7d-476b-882e-d06e9cf40e71
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines do they compare to?\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 for th...
[ "Top-$k$ replies, likes, or re-tweets, FacTweet (tweet-level), LR + All Features (chunk-level), LR + All Features (tweet-level), Tweet2vec, LR + Bag-of-words" ]
2,883
qasper
b82139b2-2778-4bf3-bc4b-1b8072598561
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What model is used as a baseline? \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 RC datasets ...
[ "QANet , BIBREF14, fine-tuned a BERT model" ]
3,415
qasper
bafb3122-a5fc-4871-b46a-a886b93264b8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are weights dynamically adjusted?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives concrete examples: for the Named Entity Recogniti...
[ "associates each training example with a weight in proportion to $(1-p)$, and this weight dynamically changes as training proceeds" ]
5,635
qasper
bdf3ec45-0f4b-45d3-97cb-1858d42265c6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset(s) do they experiment with?\n\nIntroduction\nDeep Learning approaches have achieved impressive results on various NLP tasks BIBREF0 , BIBREF1 , BIBREF2 and have become the de facto approach for any NLP task. However, the...
[ "IITB English-Hindi parallel corpus BIBREF22, ILCI English-Hindi parallel corpus" ]
2,976
qasper
c1055675-cc39-49a4-a031-15f7a3e25978
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English dataset?\n\nData\nWe build and test our MMT models on the Multi30K dataset BIBREF21 . Each image in Multi30K contains one English (EN) description taken from Flickr30K BIBREF22 and human translat...
[ "No" ]
2,505
qasper
c54348f8-79bf-4b54-a1e6-4ce0aba78e54
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which hyperparameters were varied in the experiments on the four tasks?\n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in particular tasks. Such features are of...
[ "different number of clusters, different embeddings" ]
3,565
qasper
d047256a-b15c-4e3f-9753-4e09aa46e3b4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What rouge score do they achieve?\n\nIntroduction\nLanguage model pretraining has advanced the state of the art in many NLP tasks ranging from sentiment analysis, to question answering, natural language inference, named entity recogni...
[ "Highest scores for ROUGE-1, ROUGE-2 and ROUGE-L on CNN/DailyMail test set are 43.85, 20.34 and 39.90 respectively; on the XSum test set 38.81, 16.50 and 31.27 and on the NYT test set 49.02, 31.02 and 45.55" ]
6,515
qasper
ddcb607c-c72d-4ae1-bf81-e1fc0bd42f6b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the methods that work best on academic papers also work best on Wikipedia?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. Thi...
[ "Yes" ]
5,714
qasper
e3b5916a-416f-4d17-8488-dbd11f9cc475
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the ground truth for fake news established?\n\n10pt\n1.10pt\n[ Characterizing Political Fake News in Twitter by its Meta-DataJulio Amador Díaz LópezAxel Oehmichen Miguel Molina-Solana( j.amador, axelfrancois.oehmichen11, mmolin...
[ "Ground truth is not established in the paper" ]
3,930
qasper
ea4a4acd-0991-4f8b-a2e7-74e69b8babda
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What existing dataset is re-examined and corrected for training?\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 te...
[ " UM Inventory " ]
4,069
qasper
ed82ba7f-841d-42d0-a755-e8fe066dcb49
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many tags do they look at?\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...
[ "Unanswerable" ]
4,426
qasper
f214094e-0365-425b-b465-3308dd6df6f6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the different variations of the attention-based approach which are examined?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically wom...
[ " four attention mechanisms instead of one, a projection layer for the word embeddings" ]
3,872
qasper
f8b87001-d96c-4571-a68b-98024ac9061f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the ROUGE score of the highest performing model?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applied to several real-world ...
[ "33.33" ]
5,691
qasper
f9f0ce9e-4052-4741-aa4e-dff28f5281e7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many people participated in their evaluation study of table-to-text models?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 , BIBREF4 has seen a growth in...
[ "about 500" ]
5,088
qasper
faab082d-118e-4a17-9e86-2f70c2ba5d84
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used for evaluation?\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...
[ "ARC, TREC, GARD, MLBioMedLAT" ]
8,027
qasper
1142cdd5-58ed-4e2a-81ff-aff3f1f8d219
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of repetitive and time-consuming activities does their assistant handle?\n\nIntroduction\nRobotic Process Automation (RPA) is a type of software bots that simulates hand-operated human activities like entering data into a sy...
[ "Unanswerable" ]
8,438
qasper
12f2fbb2-f579-4395-89cb-3ffd7270190a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What sentiment classification dataset 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...
[ "IMDb movie review" ]
4,697
qasper
19922f79-e25c-4493-948e-0187e0af5f3c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which toolkits do they use?\n\nIntroduction\nAs social media, specially Twitter, takes on an influential role in presidential elections in the U.S., natural language processing of political tweets BIBREF0 has the potential to help wit...
[ "BIBREF23, BIBREF17, BIBREF18, BIBREF19, BIBREF24, BIBREF25, BIBREF26" ]
2,135
qasper
24154822-ee74-4989-9436-9d1c64bd38e1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the corpus used for the task?\n\nIntroduction\nNatural languages evolve and words have always been subject to semantic change over time BIBREF1. With the rise of large digitized text resources recent NLP technologies have made...
[ "Diachronic Usage Relatedness (DURel) gold standard data set" ]
2,623
qasper
26ae6715-3609-4277-aa6e-c5edaff81055
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large are the improvements of the Attention-Sum Reader model when using the BookTest dataset?\n\nIntroduction\nSince humans amass more and more generally available data in the form of unstructured text it would be very useful to t...
[ "Answer with content missing: (Table 2) Accuracy of best AS reader results including ensembles are 78.4 and 83.7 when trained on BookTest compared to 71.0 and 68.9 when trained on CBT for Named endity and Common noun respectively." ]
5,282
qasper
27f4a0ac-8452-4a8e-8dc0-a003038ed00e
[{"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...
[ " higher tiers of the pyramid" ]
6,263
qasper
282edbb4-7e66-44dc-9c4f-7ed1fe0814dc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the invertibility condition?\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 d...
[ "The neural projector must be invertible." ]
5,842
qasper
28838afa-a2c6-40ff-b99e-4405f86fed3d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the StackExchange dataset?\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 m...
[ "around 332k questions" ]
6,248
qasper
28e8439a-f748-45c7-b3dc-69a3e54402ed
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is diversity measured?\n\nIntroduction\nAutomatically generating text to describe the content of images, also known as image captioning, is a multimodal task of considerable interest in both the computer vision and the NLP communi...
[ " we look at language constructions used and compute the corresponding diversity score as the ratio of observed number versus optimal number" ]
4,577
qasper
2cf7a284-1d33-4917-ad1a-8988c814f6a2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the ROUGE score of the highest performing model?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applied to several real-world ...
[ "33.33 average of ROUGE-1, ROUGE-2 and ROUGE-L " ]
5,691
qasper
2d99053c-c401-430b-b24f-f58d50f227d7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the tweets annotated?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually define...
[ "Unanswerable" ]
2,820
qasper
35771126-cbfe-4749-a2a3-b5767cc94c1a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How long is the dataset for each step of hierarchy?\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 t...
[ "Level A: 14100 Tweets\nLevel B: 4640 Tweets\nLevel C: 4089 Tweets" ]
3,088
qasper
4a7ec77a-23ae-452e-ba95-7f5e512ead34
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What profile metadata is used for this analysis?\n\nIntroduction\nUser profiles on social media platforms serve as a virtual introduction of the users. People often maintain their online profile space to reflect their likes and values...
[ "username, display name, profile image, location and description" ]
6,809
qasper
4d89c7ac-7148-464c-87c3-ef06ec8d5eb9
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they analyze which topics, dialects and gender are most associated with tweets?\n\nIntroduction\nDisclaimer: Due to the nature of the paper, some examples contain highly offensive language and hate speech. They don't reflect t...
[ "ascertain the distribution of: types of offensive language, genres where it is used, the dialects used, and the gender of users using such language" ]
7,113
qasper
4f63130a-de54-4149-94f2-3d8426f43e89
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the differences between this dataset and pre-existing ones?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media pl...
[ "no prior work has explored the target of the offensive language" ]
3,089
qasper
4f9b6bbc-e8b1-47f8-82fc-6c73d01e0186
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they combine audio and text sequences in their RNN?\n\nIntroduction\nRecently, deep learning algorithms have successfully addressed problems in various fields, such as image classification, machine translation, speech recogniti...
[ "encodes the information from audio and text sequences using dual RNNs and then combines the information from these sources using a feed-forward neural model" ]
4,316
qasper
53926f4f-46f5-4ca9-bbc6-cc039ba991ff
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is keyphrase diversity measured?\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...
[ "average unique predictions, illustrate the difference of predictions between our proposed models, we show an example chosen from the KP20k validation set" ]
6,245
qasper
5c783088-b1a7-459b-b04f-b78859efa870
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the images from a specific domain?\n\nIntroduction\nAutomatically generating text to describe the content of images, also known as image captioning, is a multimodal task of considerable interest in both the computer vision and the...
[ "Yes" ]
4,580
qasper
5e89ef2f-ba82-4abd-b2b1-13fa5953afad
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How long are the essays on average?\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 increasingly recogniz...
[ "204 tokens" ]
2,670
qasper
6e2a0959-7e43-4e8c-8c4e-40280d8e66fb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they obtain psychological dimensions of people?\n\nIntroduction\nBlogging gained momentum in 1999 and became especially popular after the launch of freely available, hosted platforms such as blogger.com or livejournal.com. Blog...
[ "Unanswerable" ]
1,934
qasper
87330a36-61a2-4caa-8e19-ed3164be831f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks do they experiment with?\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 classifica...
[ "text classification and text semantic matching" ]
6,476
qasper
8c9692dc-b689-4138-9db2-fca58c9c5c23
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are chunks defined?\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 for the authors, ...
[ "Chunks is group of tweets from single account that is consecutive in time - idea is that this group can show secret intention of malicious accounts." ]
2,880
qasper
a6012f66-e630-4021-9628-ae1a0e1c3033
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are chunks defined?\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 for the authors, ...
[ "sequence of $s$ tweets" ]
2,880
qasper
b1af846e-e0c8-43af-bdd3-5ee9fd23ef5b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the benchmark dataset?\n\nIntroduction\nVector-based semantic mapping models are used to represent textual structures (words, phrases, and documents) as high-dimensional meaning vectors. Typically, these models utilize textual...
[ "dataset created by ceccarelli2013learning from the CoNLL 2003 data" ]
5,383
qasper
bdc4f3fc-87b7-403d-a1b0-9a734296106c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what crowdsourcing platform was used?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people ...
[ "Amazon Mechanical Turk" ]
5,794
qasper
c0066106-bc36-481b-8591-1c3597ba30be
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are two datasets model is applied to?\n\nIntroduction\n“Ché saetta previsa vien più lenta.”\n– Dante Alighieri, Divina Commedia, Paradiso\nAntisocial behavior is a persistent problem plaguing online conversation platforms; it is ...
[ " `Conversations Gone Awry' dataset, subreddit ChangeMyView" ]
6,584
qasper
c1a29e7a-fc26-480d-a121-36234196ebc1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How larger are the training sets of these versions of ELMo compared to the previous ones?\n\nIntroduction\nWord embeddings are representations of words in numerical form, as vectors of typically several hundred dimensions. The vectors...
[ "By 14 times." ]
4,625
qasper
c6cffbca-d15d-4308-a5e1-d3225cc6ab6e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the augmented dataset?\n\nIntroduction\nAlzheimer’s disease (AD) is a neurodegenerative disease affecting over 40 million people worldwide with high costs of acute and long-term care BIBREF0 . Recruitment of partic...
[ "609" ]
3,523
qasper
d433cad6-dc63-493a-9e8f-3d2525a65e16
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their model improve interpretability compared to softmax transformers?\n\nIntroduction\nThe Transformer architecture BIBREF0 for deep neural networks has quickly risen to prominence in NLP through its efficiency and performan...
[ "We introduce sparse attention into the Transformer architecture" ]
7,823
qasper
d451f25a-9a68-4eb0-bee3-735017c01c62
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What do they mean by global and local context?\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 should f...
[ "global (the whole document) and the local context (e.g., the section/topic) " ]
5,768
qasper
dde0f3b1-b43c-4e9f-8a5b-d9adbd3bf8e2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they deal with unknown distribution senses?\n\nIntroduction\nThe focus of the word sense disambiguation (WSD) task is polysemy, i.e. words having several substantially different meanings. Two common examples are bank (riverside...
[ "The Näive-Bayes classifier is corrected so it is not biased to most frequent classes" ]
4,989
qasper
edb4016f-3c83-4611-8a51-eed1428b35d3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets do they use?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/\nEntity linking (EL), mapping entity menti...
[ "CoNLL-YAGO, TAC2010, ACE2004, AQUAINT, WW" ]
5,742
qasper