uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
f9324802-3566-47b9-ab62-14e23da31b74 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many participants were trying this communication game?\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 autocomplet... | [
"100 "
] | 2,584 | qasper |
04ff10dd-445f-4769-8634-b493daf90ce4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the quality of the data empirically evaluated? \n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascadin... | [
"computed sentence-level BLEU, We manually inspected examples where the source transcript was identical to the translation, measured the perplexity of the translations, computed the ratio of English characters in the translations, calculate similarity scores between transcripts and translations"
] | 3,602 | qasper |
1376f456-0c97-4885-8957-90fc534eef8c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors report results only on English data?\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 differen... | [
"Unanswerable"
] | 6,266 | qasper |
36eead66-23f5-4c4b-94c5-e5adbaac7d57 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were crowd workers instructed to identify important elements in large document collections?\n\nIntroduction\nMulti-document summarization (MDS), the transformation of a set of documents into a short text containing their most impo... | [
"provide only a description of the document cluster's topic along with the propositions"
] | 5,680 | qasper |
3757f69c-db90-47d4-a0e7-8fadcd981cbb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of model do they use?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, including essay scoring... | [
"Inception V3, biLSTM"
] | 5,707 | qasper |
45746518-2516-4498-be8a-e98b10bda0d4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors mention any downside of lemmatizing input before training ELMo?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems.... | [
"Yes"
] | 4,031 | qasper |
550f2789-ecc5-4392-a9c6-2029cd4ce31f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is quantitative improvement of proposed method (the best variant) w.r.t. baseline (the best variant)?\n\nIntroduction\nKnowledge and/or data is often modeled in a structure, such as indexes, tables, key-value pairs, or triplets. ... | [
"Hierarchical-k"
] | 7,022 | qasper |
587e7c85-d7ac-41f5-866a-2e2dac563017 | [{"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 BIBREF23 , BIBREF24, Yelp restaurant reviews dataset, restaurant reviews dataset as part of a Kaggle competition BIBREF26"
] | 3,541 | qasper |
63f037a5-8baf-400c-84e8-80213e4714a7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the hyperparameters of the bi-GRU?\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... | [
"They use the embedding layer with a size 35 and embedding dimension of 300. They use a dense layer with 70 units and a dropout layer with a rate of 50%."
] | 3,194 | qasper |
6b84cd51-6e35-459c-b44c-4abbce3c15c8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are strong baselines model is compared to?\n\nIntroduction\nChinese word segmentation (CWS) is a task for Chinese natural language process to delimit word boundary. CWS is a basic and essential task for Chinese which is written w... | [
"Baseline models are:\n- Chen et al., 2015a\n- Chen et al., 2015b\n- Liu et al., 2016\n- Cai and Zhao, 2016\n- Cai et al., 2017\n- Zhou et al., 2017\n- Ma et al., 2018\n- Wang et al., 2019"
] | 5,084 | qasper |
6d5cb365-f5fc-474e-bb85-77d79b70caf1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What error types is their model more reliable for?\n\nIntroduction\nSequence-to-sequence (seq2seq) transformations have recently proven to be a successful framework for several natural language processing tasks, like: machine translat... | [
"spelling, word order and grammatical errors"
] | 6,337 | qasper |
7986f8ec-a6c3-4369-828f-784f6346bc5e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of classifiers?\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 and un... | [
"Using F1 Micro measure, the KNN classifier perform 0.6762, the RF 0.6687, SVM 0.6712 and MLP 0.6778."
] | 2,203 | qasper |
7caf9608-6450-46b0-a8b5-ec57b9fcb623 | [{"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... | [
"English"
] | 3,186 | qasper |
813a3194-7a72-459a-b789-b6de2c5c35e6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of celebrities do they obtain tweets from?\n\nIntroduction\nSocial media platforms, particularly microblogging services such as Twitter, have become increasingly popular BIBREF0 as a means to express thoughts and opinions. T... | [
"Celebrities from varioius domains - Acting, Music, Politics, Business, TV, Author, Sports, Modeling. "
] | 5,282 | qasper |
99653c56-c334-4d31-a1f4-fefcb528fe8d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the model have attention?\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 w... | [
"Yes"
] | 3,046 | qasper |
a1049265-7415-470e-8a46-3630d7b35271 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is their explanation for the effectiveness of back-translation?\n\nIntroduction \nThe new generation of Neural Machine Translation (NMT) systems is known to be extremely data hungry BIBREF0 . Yet, most existing NMT training pipel... | [
"when using BT, cases where the source is shorter than the target are rarer; cases when they have the same length are more frequent, automatic word alignments between artificial sources tend to be more monotonic than when using natural sources"
] | 5,632 | qasper |
a9307a30-2c9e-4031-aa8f-6d9adbcdb8db | [{"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, RANDOM, JUMP"
] | 3,009 | qasper |
ce42ca91-e042-499d-98c0-eb4f51763269 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does final model rate on Likert scale?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and dry captions which are... | [
"average content score across the paintings is 3.7, average creativity score is 3.9, average style score is 3.9"
] | 2,140 | qasper |
eb2fbcc2-e596-4000-a273-8b4e9d9d7770 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\n\nIntroduction\nSemantic Role Labeling (SRL) has emerged as an important task in Natural Language Processing (NLP) due to its applicability in information extraction, question answering, and other NLP tas... | [
"same baseline as used by lang2011unsupervised"
] | 5,268 | qasper |
ec711a18-29f3-4e0f-84d6-4daa21954f79 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used to assess the performance of the system?\n\nIntroduction\nTopic identification (topic ID) on speech aims to identify the topic(s) for given speech recordings, referred to as spoken documents, where the topics ar... | [
"LORELEI datasets of Uzbek, Mandarin and Turkish"
] | 4,765 | qasper |
eca8a6cc-1c46-4a60-b983-f141fe9ae8fc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nSpeech-to-Text translation (ST) is essential for a wide range of scenarios: for example in emergency calls, where agents have to respond emergent requests in a foreign language BIBREF0; or in o... | [
"Vanilla ST baseline, encoder pre-training, in which the ST encoder is initialized from an ASR model, decoder pre-training, in which the ST decoder is initialized from an MT model, encoder-decoder pre-training, where both the encoder and decoder are pre-trained, many-to-many multi-task model where the encoders and ... | 7,491 | qasper |
136e88e5-adb7-4c18-a829-39ce6bcff618 | [{"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 |
18f77ca3-2ee1-4ca0-b5dc-eda3e1929f34 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the speech corpus?\n\nIntroduction\nTypical speech-to-text translation systems pipeline automatic speech recognition (ASR) and machine translation (MT) BIBREF0 . But high-quality ASR requires hundreds of hours of t... | [
"104 telephone calls, transcripts contain 168,195 Spanish word tokens, translations contain 159,777 English word tokens"
] | 2,067 | qasper |
2d3ac7eb-4e91-466b-9ed2-3ae1d4f0e9a4 | [{"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... | [
"No"
] | 5,714 | qasper |
3514be6f-86f8-463f-aada-ce15b3141e19 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Internet to spread its ideology, radicalize individuals, and recruit them to their cause... | [
"Yes"
] | 4,670 | qasper |
3ae099fe-644b-484b-8825-b74ba2f020b1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for evaluation?\n\nIntroduction\nIn the kitchen, we increasingly rely on instructions from cooking websites: recipes. A cook with a predilection for Asian cuisine may wish to prepare chicken curry, but may not kn... | [
" Distinct-1/2, UMA = User Matching Accuracy, MRR\n= Mean Reciprocal Rank, PP = Pairwise preference over baseline (evaluated for 310 recipe pairs per model)"
] | 3,949 | qasper |
4370df13-3160-41dd-b2f6-e568849565aa | [{"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"
] | 6,775 | qasper |
52cf5212-9790-4bd1-9d5f-abfeb9ec5ff7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is English poem description of the painting dataset?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple and dry ... | [
"Unanswerable"
] | 2,141 | qasper |
54d0c252-320d-4ac2-b21b-fbdb8538a5e4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is their data set?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, including essay scoring (q... | [
"a sample of 29,794 wikipedia articles and 2,794 arXiv papers "
] | 5,706 | qasper |
576af553-3d6d-4961-9910-d26e51ed7a2d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the answered questions measure for the usefulness of the answer?\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&... | [
"No"
] | 2,011 | qasper |
5eb4e552-cae1-4bea-9d85-12ae32f4e9b0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the dimension of the embeddings?\n\nIntroduction\nEarlier studies on stock market prediction are based on the historical stock prices. Later studies have debunked the approach of predicting stock market movements using histori... | [
"300"
] | 3,162 | qasper |
65fc342d-b0f0-4b50-b20a-33c0575ab933 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which multiple datasets did they train on during joint training?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple... | [
"BF, BA, SFU and Sherlock"
] | 3,292 | qasper |
74c480bb-8fc4-4ea8-91cc-c99bcbc6dc0c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they identify discussions of LGBTQ people in the New York Times?\n\nKeywords:\ncomputational sociolinguistics, dehumanization, lexical variation, language change, media, New York Times, LGBTQ\nWarning: this paper contains mater... | [
"act paragraphs containing any word from a predetermined list of LGTBQ terms "
] | 17,780 | qasper |
929cb087-29e0-4c06-9f64-2e527d69d4dd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what aspects of conversation flow do they look at?\n\nIntroduction\nPublic debates are a common platform for presenting and juxtaposing diverging viewpoints As opposed to monologues where speakers are limited to expressing their own b... | [
"—promoting one's own points and attacking the opponents' points"
] | 3,176 | qasper |
98d42423-cacd-429b-8565-8d42c5d07869 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they train their models on?\n\nIntroduction\nRelation classification is the task of assigning sentences with two marked entities to a predefined set of relations. The sentence “We poured the <e1>milk</e1> into the <e2... | [
"SemEval 2010 task 8 BIBREF8"
] | 3,318 | qasper |
b89d15cc-4c47-40b3-bdb8-6864eac17998 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the lexicon the same for all languages?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known ... | [
"Yes"
] | 2,612 | qasper |
c5de06cd-fb89-4d28-8291-65e4b4f8fcd0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What does a node in the network approach repesent?\n\nIntroduction\nThe polarization of actors' expressed preferences is a fundamental concern for studies of legislatures, court systems, and international politics BIBREF0 , BIBREF1 , ... | [
"Unanswerable"
] | 10,902 | qasper |
cec6a82f-fba6-4826-92ab-0abea52edc35 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the best reported system?\n\nIntroduction\nSarcasm is an intensive, indirect and complex construct that is often intended to express contempt or ridicule . Sarcasm, in speech, is multi-modal, involving tone, body-language and ... | [
"Gaze Sarcasm using Multi Instance Logistic Regression."
] | 4,865 | qasper |
cef32f6e-9bfe-40d8-b220-5b3c44fcf48a | [{"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 |
da7a089c-eeee-494a-bfa8-320db378b223 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the spatial aspect of the EEG signal computed?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIBREF0 , BIBREF1 . In ... | [
"we use a CNN BIBREF19 , in particular a four-layered 2D CNN stacking two convolutional and two fully connected hidden layers."
] | 3,284 | qasper |
077fd34d-1562-4b50-be5e-baefdb4bc03d | [{"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... | [
"machine translation platform Apertium BIBREF5"
] | 3,099 | qasper |
10486c21-2f9c-42af-8830-714f7f3d8606 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used for evaluation?\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 pre-trai... | [
"United Nations Parallel Corpus, IIT Bombay corpus, OpenSubtitles 2018"
] | 5,300 | qasper |
125f890f-66a7-40ca-8ba3-e5384bd4aad2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics are used?\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 title ma... | [
"standard accuracy metric"
] | 3,077 | qasper |
15aba3ce-7901-4d23-b076-380c26bc0406 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of SFU Review corpus?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple use-cases, like systems t... | [
"Unanswerable"
] | 3,291 | qasper |
26ee92c5-a398-4a4b-a984-df7dbfaa680a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is evaluation performed?\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 it possi... | [
"Spearman's rank-order correlation"
] | 2,619 | qasper |
29759d5c-41b8-4c52-864f-4cf319d2d1dd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the authors show that their learned policy generalize better than existing solutions to unseen games?\n\nIntroduction\nText-based games became popular in the mid 80s with the game series Zork BIBREF1 resulting in many different... | [
"promising results by solving almost half of the unseen games, most of the lost games are in the hardest set, where a very long sequence of actions is required for winning the game"
] | 6,946 | qasper |
2cd93b58-7cbb-4e30-b52d-7c03214e7d50 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which qualitative metric are used for evaluation?\n\nIntroduction\nKnowledge and/or data is often modeled in a structure, such as indexes, tables, key-value pairs, or triplets. These data, by their nature (e.g., raw data or long time-... | [
" Relation Generation (RG) , Content Selection (CS), Content Ordering (CO)"
] | 7,008 | qasper |
34637b2e-7953-4640-ab2b-7127cbc2614b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is masked document generation?\n\nIntroduction\nLarge pre-trained language models BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4 improved the state-of-the-art of various natural language understanding (NLU) tasks such as question an... | [
"recovers a masked document to its original form"
] | 6,833 | qasper |
46ab1b04-2959-40f4-932a-8d1ac7c486a1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is novel about their document-level encoder?\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, name... | [
"Bert model have a maximum length of 512; we overcome this limitation by adding more position embeddings, we insert external [cls] tokens at the start of each sentence, and each [cls] symbol collects features for the sentence preceding it, document representations are learned hierarchically"
] | 6,517 | qasper |
4be7302a-c2bd-4f25-b6fe-388b689e1c37 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method's improvements of F1 for NER task for English and Chinese datasets?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives con... | [
"For English datasets including CoNLL2003 and OntoNotes5.0, our proposed method outperforms BERT-MRCBIBREF38 by +0.29 and +0.96 respectively., huge performance boosts on Chinese datasets, achieving F1 improvements by +0.97 and +2.36 on MSRA and OntoNotes4.0, respectively"
] | 5,647 | qasper |
4ceffd25-a8d0-4a62-9fdf-0b20bec41e31 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the McGurk effect?\n\nIntroduction\nA growing body of work on adversarial examples has identified that for machine-learning (ML) systems that operate on high-dimensional data, for nearly every natural input there exists a smal... | [
"a perceptual illusion, where listening to a speech sound while watching a mouth pronounce a different sound changes how the audio is heard"
] | 4,431 | qasper |
536a9f39-489d-41a8-8307-441ea69faca5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines used?\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 able to infe... | [
"Unif and Stopword"
] | 2,582 | qasper |
57b107fe-44cd-4471-8db2-e7b4d3853232 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which languages are explored?\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 to associat... | [
"Bulgarian, Croatian, Czech, Danish, English, French, German, Indonesian, Italian, Norwegian, Persian, Polish, Portuguese, Slovenian, Spanish and Swedish"
] | 3,758 | qasper |
5f5c29d3-7654-455f-8785-353c215bd1cf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what data did they use?\n\nIntroduction\nLong short term memory (LSTM) units BIBREF1 are popular for many sequence modeling tasks and are used extensively in language modeling. A key to their success is their articulated gating struct... | [
" Penn Treebank, WikiText2"
] | 4,613 | qasper |
b2e6ec33-1cf7-4d56-8d61-78af9ffdb9e0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who are the crowdworkers?\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 with ... | [
"located in the US, hired on the BIBREF22 platform"
] | 2,134 | qasper |
bc322c9f-b878-481b-8f19-3cde926ad5f8 | [{"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 distinct review keywords "
] | 4,424 | qasper |
c56f4ad1-fbae-4eb8-adaa-9620329e6757 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What extracted features were most influencial on performance?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and aim individua... | [
"BERT"
] | 2,438 | qasper |
c8398caa-1659-4fd9-90b4-ea192c0291d0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How well did the baseline perform?\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 utteranc... | [
"accuracy of 30.3% on single sentences and 0.3 on complete paragraphs"
] | 3,011 | qasper |
cd38d575-65cd-43bf-b7dc-9613437633c6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are prominent topics idenified in Dabiq and Rumiyah?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Internet to spread its ideology, radicalize individuals, and recruit them to... | [
"Using NMF based topic modeling and their coherence prominent topics are identified"
] | 4,677 | qasper |
e1d58d68-8671-4dcf-989b-d2c81ff11ab7 | [{"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 extracted from ELS's have issues because of low precision rates BIBREF11 and design challenges in training datasets BIBREF12 . These issues can be summarized into two parts: ambiguity and coarseness., the linked entities may also be too common to be considered an entity."
] | 5,268 | qasper |
ec9dfd72-7ce8-454f-8da5-f39ceca165a9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the previous state of the art for this task?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quality education from reputed universities to students a... | [
"hLSTM"
] | 4,780 | qasper |
f5786c0b-1e93-40a0-8265-7f760633bdb9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which corpora does this paper analyse?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous studies have been conducted in order to evaluate the presence of wome... | [
"ESTER1, ESTER2, ETAPE, REPERE"
] | 5,375 | qasper |
2fe882ad-35fd-474c-b151-426521dc91b2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used?\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 communiti... | [
"ShapeWorldICE datasets: OneShape, MultiShapes, TwoShapes, MultiShapes, Count, and Ratio"
] | 4,577 | qasper |
326941e0-b9f0-48ee-9946-e4ab9a5df5fc | [{"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... | [
"They compute the gradient of the output at each time step with respect to the input words to decide the importance."
] | 5,827 | qasper |
3573bb3d-f614-4d64-997a-f42d1ce4ee5e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the hashtag and SemEval datasets contain only English data?\n\nIntroduction\nA hashtag is a keyphrase represented as a sequence of alphanumeric characters plus underscore, preceded by the # symbol. Hashtags play a central role in o... | [
"Yes"
] | 5,418 | qasper |
382a9c60-41d9-40e3-b7cd-22655b966a2a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the user-defined keywords?\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 n... | [
"terms common to hosts' descriptions of popular Airbnb properties, like 'subway', 'manhattan', or 'parking'"
] | 3,506 | qasper |
3c348c91-03a5-4863-bf51-f566eefc0719 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used?\n\nIntroduction\nThe cognitive processes involved in human language comprehension are complex and only partially identified. According to the dual-stream model of speech comprehension BIBREF1 , sound waves are ... | [
"the ERP data: BIBREF0"
] | 2,364 | qasper |
4ba412d1-1cda-49eb-97db-acbb7b55ab48 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators participated?\n\nIntroduction\nCancer is one of the leading causes of death in the world, with over 80,000 deaths registered in Canada in 2017 (Canadian Cancer Statistics 2017). A computer-aided system for cancer d... | [
"Unanswerable"
] | 2,755 | qasper |
4f0055a6-4c72-41f7-a024-6081858f1131 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Ngrams of which length are aligned using PARENT?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 , BIBREF4 has seen a growth in interest with the rise of sequ... | [
"Unanswerable"
] | 5,085 | qasper |
7354e3fe-4840-4886-a3a5-30c1a2d9c54c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation metrics were used?\n\nIntroduction\nAccurate grapheme-to-phoneme conversion (g2p) is important for any application that depends on the sometimes inconsistent relationship between spoken and written language. Most promi... | [
"PER, WER, WER 100"
] | 4,276 | qasper |
7e73f58a-94da-41f7-8e5f-cc4da880ace0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the benchmark dataset and is its quality high?\n\nIntroduction\nMicroblogging such as Twitter and Weibo is a popular social networking service, which allows users to post messages up to 140 characters. There are millions of ac... | [
"Social Honeypot dataset (public) and Weibo dataset (self-collected); yes"
] | 3,617 | qasper |
93597980-9dc2-4f00-912a-1386b5dd0951 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data is used in experiments?\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 emotio... | [
"Wang et al., CrowdFlower dataset "
] | 3,189 | qasper |
a42b33eb-ab06-49bc-b60d-6a9345f82057 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which approach out of two proposed in the paper performed better in experiments?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Wo... | [
"CJFA encoder "
] | 5,212 | qasper |
ac6f6578-0d47-4082-b70b-d6986b0e3bd7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what way does LiLi imitate how humans acquire knowledge and perform inference during an interactive conversation?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural languag... | [
"Whenever we encounter an unknown concept or relation while answering a query, we perform inference using our existing knowledge. If our knowledge does not allow us to draw a conclusion, we typically ask questions to others to acquire related knowledge and use it in inference. "
] | 8,590 | qasper |
acadd9f6-acc1-41c8-9f33-40e4a902789b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are hashtag features?\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 defined as... | [
"hashtag features contain whether there is any hashtag in the tweet"
] | 2,819 | qasper |
af438704-ef96-4fea-a6f7-f15ae26d2bbe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is the Twitter dataset?\n\nIntroduction\nRecently, people have started looking at online forums either as a primary or secondary source of counseling services BIBREF0. BIBREF1 reported that over the first five years of opera... | [
"1,873 Twitter conversation threads, roughly 14k tweets"
] | 4,713 | qasper |
bfbd5c67-2c79-4dd5-9531-280715e96c4f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which demographic dimensions of people do they obtain?\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... | [
"density of users, gender distribution"
] | 1,934 | qasper |
cd7e2633-459b-4732-9da4-7b94f12205c2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the models used for the baseline of the three NLP tasks?\n\nIntroduction\nRecent years have seen unprecedented progress for Natural Language Processing (NLP) on almost every NLP subtask. Even though low-resource settings have... | [
"state-of-the-art Transformer architecture, Kaldi, speech clustergen statistical speech synthesizer"
] | 4,184 | qasper |
d5fb0346-0f28-4d45-b8c0-39c138a1115c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where do they obtain the news videos from?\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... | [
"NowThisNews Facebook page"
] | 3,080 | qasper |
dfc820f6-3c32-4f0f-9689-14b9f2a1aaf9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the vocabulary of word-like or phoneme-like units automatically discovered?\n\nIntroduction\nTopic identification (topic ID) on speech aims to identify the topic(s) for given speech recordings, referred to as spoken documents, ... | [
"Zero Resource Toolkit (ZRTools) BIBREF7"
] | 4,768 | qasper |
f216e043-40bb-4c15-aa88-3bae361dea04 | [{"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... | [
" SemEval-2016 “Sentiment Analysis in Twitter”"
] | 3,586 | qasper |
f8c9fdad-9a96-4a18-ad47-b007bd4c7421 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was their character error rate?\n\nIntroduction\nRecently, deep neural network has been widely employed in various recognition tasks. Increasing the depth of neural network is a effective way to improve the performance, and convo... | [
"2.49% for layer-wise training, 2.63% for distillation, 6.26% for transfer learning."
] | 5,551 | qasper |
f9f42dc7-7405-424c-a875-cbd42604205c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation protocols are provided?\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 th... | [
"three experimental setups with different numbers of speakers in the evaluation set, three experimental setups with different number of speaker in the evaluation set are defined, first one, respondents with at least 17 recording sessions are included to the evaluation set, respondents with 16 sessions to the devel... | 5,097 | qasper |
ff33ae1d-11e2-4fd3-8b82-c215cdaa0438 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are four major corpora of French broadcast?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous studies have been conducted in order to evaluate the presen... | [
"ESTER1, ESTER2, ETAPE, REPERE"
] | 5,377 | qasper |
0d4781d9-f7de-476f-9336-111b77095058 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets do they use?\n\nIntroduction\nAdversarial examples, a term introduced in BIBREF0, are inputs transformed by small perturbations that machine learning models consistently misclassify. The experiments are conducted in the ... | [
"1 IMDB dataset and 2 Yelp datasets"
] | 6,094 | qasper |
1d516bab-f826-41df-8e29-169a8dd40f6c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they define robustness of a model?\n\nIntroduction\nWe posses a wealth of prior knowledge about many natural language processing tasks. For example, in text categorization, we know that words such as NBA, player, and basketball... | [
"ability to accurately classify texts even when the amount of prior knowledge for different classes is unbalanced, and when the class distribution of the dataset is unbalanced"
] | 5,001 | qasper |
22241e11-73c0-4add-9fcc-80f1676a0a24 | [{"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... | [
" English reviews , restaurant reviews from four different languages (Spanish, Turkish, Dutch, Russian)"
] | 3,541 | qasper |
3a7e8d4a-10c8-4cee-8206-dece2f446fea | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate only on English datasets?\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... | [
"Yes"
] | 2,800 | qasper |
5c1212e6-9206-4225-bf7c-ff6e55468aa3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their model suffer exhibit performance drops when incorporating word importance?\n\nIntroduction\nNeural machine translation (NMT) has achieved the state-of-the-art results on a mass of language pairs with varying structural diff... | [
"No"
] | 5,822 | qasper |
64839de4-2e5b-4d29-b27b-3defbf74a7d3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Can the findings of this paper be generalized to a general-purpose task?\n\nIntroduction\nIt is well known that language has certain structural properties which allows natural language speakers to make “infinite use of finite means\" ... | [
"Yes"
] | 2,570 | qasper |
6a7153ed-d24d-4af2-8333-0dac0fbaa4ea | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they show there is space for further improvement?\n\nIntroduction\nSince humans amass more and more generally available data in the form of unstructured text it would be very useful to teach machines to read and comprehend such... | [
" by testing humans on a random subset of 50 named entity and 50 common noun validation questions that the psr ensemble could not answer correctly"
] | 5,274 | qasper |
9efd4c5d-97e1-4e1c-9586-d827616fa45d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the black-box probes used?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs) derived from pretraining language models o... | [
"Probes are linear models trained on frozen cwrs to make predictions about linguistic (syntactic and semantic) properties of words and phrases."
] | 3,681 | qasper |
9ffbd8b5-9eeb-4318-9f13-3bd8822ba0fc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the different modules in Macaw?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy ... | [
"Co-Reference Resolution, Query Generation, Retrieval Model, Result Generation"
] | 2,272 | qasper |
ab43cc4a-bcfa-4014-a387-11452081b078 | [{"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... | [
"Transformer over BERT (ToBERT)"
] | 3,718 | qasper |
b6d18a4a-bdbf-48d0-b13f-9d0813899f52 | [{"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... | [
"a simple word-level encoder, The encoder is essentially the same as tweet2vec, with the input as words instead of characters."
] | 3,476 | qasper |
c3d9aaba-bc7f-4cc3-84ee-a4f0aec7b63d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which approaches have been applied to solve word segmentation in Vietnamese?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural language ... | [
"Maximum matching, Hidden Markov model , Maximum Entropy, Conditional Random Fields , Support Vector Machines"
] | 4,686 | qasper |
caa49f6b-12cb-497d-90b6-e758c8a45d2e | [{"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... | [
"Unanswerable"
] | 5,274 | qasper |
cf079074-4f80-48cf-9ab5-91da96e74bc2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many humans evaluated the results?\n\nIntroduction\nMachine translation has made remarkable progress, and studies claiming it to reach a human parity are starting to appear BIBREF0. However, when evaluating translations of the who... | [
"Unanswerable"
] | 5,127 | qasper |
d7c7617d-5880-4da3-9b57-4abf4d6ffa0f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is pseudo-perplexity defined?\n\nIntroduction\nLanguage modeling is a probabilistic description of language phenomenon. It provides essential context to distinguish words which sound similar and therefore has one of the most usefu... | [
"Answer with content missing: (formulas in selection): Pseudo-perplexity is perplexity where conditional joint probability is approximated."
] | 2,734 | qasper |
d947561e-c813-416a-87f4-7b5e16f3033e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors also analyze transformer-based architectures?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/.\nSentenc... | [
"No"
] | 5,774 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.