uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
ed63b415-2ece-43c8-9ac2-bb35e7dc4f83 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of online harassment are studied?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassment becomes ve... | [
"indirect, physical, sexual"
] | 3,866 | qasper |
ffe10883-7849-44b6-87b4-b20ffc89ac4f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large are the textual descriptions of entities?\n\nIntroduction\nKnowledge graphs have been proved to benefit many artificial intelligence applications, such as relation extraction, question answering and so on. A knowledge graph ... | [
"Unanswerable"
] | 5,215 | qasper |
0a32e175-25d6-4993-ac3a-dbfd5061a35f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets were used?\n\nIntroduction\nModern Standard Arabic (MSA) and Classical Arabic (CA) have two types of vowels, namely long vowels, which are explicitly written, and short vowels, aka diacritics, which are typically omitted... | [
"the diacritized corpus that was used to train the RDI BIBREF7 diacritizer , WikiNews , a large collection of fully diacritized classical texts"
] | 7,070 | qasper |
0e2aca56-fec2-45c2-a34c-5c76a2ea8909 | [{"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... | [
"combines the information from these sources using a feed-forward neural model"
] | 4,316 | qasper |
111297a1-aaa1-41f5-ab84-70921eec51fa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which multilingual approaches do they compare with?\n\nIntroduction\nAlthough Neural Machine Translation (NMT) has dominated recent research on translation tasks BIBREF0, BIBREF1, BIBREF2, NMT heavily relies on large-scale parallel da... | [
"multilingual NMT (MNMT) BIBREF19"
] | 5,434 | qasper |
1365276e-aa42-4e47-9b58-9b0537c18452 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is their created dataset?\n\nProblem Statement\nSpoken conversations still remain the most natural and effortless means of human communication. Thus a lot of valuable information is conveyed and exchanged in such an unstructur... | [
"353 conversations from 40 speakers (11 nurses, 16 patients, and 13 caregivers), we build templates and expression pools using linguistic analysis"
] | 4,626 | qasper |
24748fc3-d55f-4796-8756-f89bd09cf99e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they train their model starting from a checkpoint?\n\nIntroduction\nThe ability of semantic reasoning is essential for advanced natural language understanding (NLU) systems. Many NLU tasks that take sentence pairs as input, such as... | [
"No"
] | 5,594 | qasper |
2a00319e-e388-4800-b7e9-2cb94b8741f7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were the baselines?\n\nIntroduction\nConventional automatic speech recognition (ASR) systems typically consist of several independently learned components: an acoustic model to predict context-dependent sub-phoneme states (senone... | [
"LF-MMI Attention\nSeq2Seq \nRNN-T \nChar E2E LF-MMI \nPhone E2E LF-MMI \nCTC + Gram-CTC"
] | 2,754 | qasper |
3714ccad-ee13-47e2-a077-84ce0d0a84fc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they obtain the lexicon?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known then the ap... | [
"built over all the data and therefore includes the vocabulary from both the training and testing sets"
] | 2,610 | qasper |
393a3854-8b1a-473c-8f63-d450970c0fe0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the sources of the datasets?\n\nIntroduction\nFollowing developing news stories is imperative to making real-time decisions on important political and public safety matters. Given the abundance of media providers and language... | [
"rupnik2016news"
] | 4,222 | qasper |
3ddd41dc-cdcf-4b6a-9961-9bd04281878c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language(s) is/are represented in the dataset?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassment bec... | [
"english"
] | 3,870 | qasper |
3f6c72b1-4fea-4efc-bfea-d0d6b7780711 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What alternative to Gibbs sampling is used?\n\nIntroduction\nWith the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter) and news media sites (e.g. Google news) have become important s... | [
"generator network to capture the event-related patterns"
] | 5,495 | qasper |
4600fb25-a69a-4dc7-851b-2bd5a660ddf3 | [{"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... | [
"Classification system use n-grams, bag-of-words, common words and hashtags as features and SVM, random forest, extra tree and NB classifiers."
] | 3,611 | qasper |
549073f9-7757-4212-bf99-45d6486613e7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is the dataset of hashtags sourced?\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 online communication by ... | [
"Stanford Sentiment Analysis Dataset BIBREF36"
] | 5,414 | qasper |
568b9197-3b87-4cf9-bdad-30d7b935c061 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How id Depechemood trained?\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. In comparison t... | [
"researchers asked subjects to report their emotions after reading each article, multiplied the document-emotion matrix and word-document matrix to derive emotion-word matrix for these words, Depechemood simply creates dictionaries of words where each word has scores between 0 and 1 for all of these 8 emotion categ... | 4,669 | qasper |
62ba0084-a378-411a-adac-5d833f426239 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which other methods do they compare with?\n\nIntroduction\nSummarization of large texts is still an open problem in language processing. People nowadays have lesser time and patience to go through large pieces of text which make autom... | [
"Lead-3, Lead-1-AMR"
] | 5,731 | qasper |
665ab369-2afc-4695-8f6c-9365f6c0eda7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what way is the offensive dataset not biased by topic, dialect or target?\n\nIntroduction\nDisclaimer: Due to the nature of the paper, some examples contain highly offensive language and hate speech. They don't reflect the views of... | [
"our methodology does not use a seed list of offensive words"
] | 7,112 | qasper |
6756fbe0-e30d-48ff-8824-4b40f82f501c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they focus on Reading Comprehension or multiple choice question answering?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly prov... | [
"multiple-choice"
] | 9,206 | qasper |
7385e50c-dfc4-48e1-b448-d3a57452fc0f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What source-target language pairs were used in this work? \n\nIntroduction\nReading Comprehension (RC) has become a central task in natural language processing, with great practical value in various industries. In recent years, many l... | [
"En-Fr, En-Zh, En-Jp, En-Kr, Zh-En, Zh-Fr, Zh-Jp, Zh-Kr to English, Chinese or Korean"
] | 3,418 | qasper |
8c1c86d1-7f34-4314-b81a-97fb6fadbb4c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset did they use?\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 semantic q... | [
"A dataset provided by BioASQ consisting of questions, gold standard documents, snippets, concepts and ideal and ideal answers."
] | 9,715 | qasper |
a3832cbd-e7e1-4e61-be59-f7025cd03b2d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What meaningful information does the GRU model capture, which traditional ML models do not?\n\nIntroduction\nThere have been many advances in machine learning methods which help machines understand human behavior better than ever. One... | [
" the context and sequential nature of the text"
] | 3,199 | qasper |
b368a481-ccd0-48e1-9f29-77f47941b0f5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evidence do the authors present that the model can capture some biases in data annotation and collection?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to comm... | [
"The authors showed few tweets where neither and implicit hatred content exist but the model was able to discriminate"
] | 5,709 | qasper |
b588bc18-2c41-420c-b2bd-bc5b6f1c63d6 | [{"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... | [
"DTA18, DTA19"
] | 2,623 | qasper |
deda85c4-36d5-4c25-9977-a7f986003d0f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why do they experiment with RNNs instead of transformers for this task?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the ... | [
"Unanswerable"
] | 5,909 | qasper |
e05e1d4e-cab8-4d98-b119-bb1dc732a1b7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What background knowledge do they leverage?\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 basketba... | [
"labelled features, which are words whose presence strongly indicates a specific class or topic"
] | 4,998 | qasper |
e0801f5c-bfc4-495c-af0c-a102e6bb94e8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluations methods do they take?\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to train and evaluate neural network models that ge... | [
"Unanswerable"
] | 2,926 | qasper |
ed42b7af-86e7-4e8f-b7b9-8a49aaa19264 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\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 whole documents rat... | [
"Transformer base, two-pass CADec model"
] | 5,125 | qasper |
f436818f-46ba-4010-b304-771c744a5901 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what ml based approaches were compared?\n\nIntroduction\nQuestion classification (QC) deals with question analysis and question labeling based on the expected answer type. The goal of QC is to assign classes accurately to the question... | [
"Multi-Layer Perceptron, Naive Bayes Classifier, Support Vector Machine, Gradient Boosting Classifier, Stochastic Gradient Descent, K Nearest Neighbour, Random Forest"
] | 2,875 | qasper |
fb4f3e61-f4ee-482e-b701-3c577cb9f45d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How better does new approach behave than existing solutions?\n\nIntroduction\nText-based games became popular in the mid 80s with the game series Zork BIBREF1 resulting in many different text-based games being produced and published B... | [
" On the other hand, phase 1 of Go-Explore finds an optimal trajectory with approximately half the interactions with the environment, Moreover, the trajectory length found by Go-Explore is always optimal (i.e. 30 steps) whereas both DQN++ and DRQN++ have an average length of 38 and 42 respectively., Especially inte... | 6,938 | qasper |
08b12502-2991-42ef-b4f6-f63b157183e2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of subwords do they incorporate in their model?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, ... | [
"n-gram subwords, unsupervised morphemes identified using Morfessor BIBREF11 to learn whether more linguistically motivated subwords "
] | 3,208 | qasper |
0962dcb0-7531-4626-b491-8095662fcb83 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is datasets for sentiment analysis balanced?\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 pote... | [
"No"
] | 2,135 | qasper |
13f46e0e-e4c0-42e6-8e9e-426996bd23f8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset do they use?\n\nIntroduction\nPre-training of language models has been shown to provide large improvements for a range of language understanding tasks BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . The key idea is to train a lar... | [
"German newscrawl, English newscrawl, WMT'18 English-German (en-de) news, WMT'18 English-Turkish (en-tr) news task, WMT'18 English-German (en-de) news translation task and we validate our findings on the WMT'18 English-Turkish (en-tr) news task"
] | 2,666 | qasper |
1745b586-d0b2-4956-b4c9-b5d36e514cec | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interac... | [
"Unanswerable"
] | 5,699 | qasper |
1f161194-7673-4ff0-9e58-c5d85c57868e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what phenomena do they mention is hard to capture?\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 translation... | [
"Four discourse phenomena - deixis, lexical cohesion, VP ellipsis, and ellipsis which affects NP inflection."
] | 5,130 | qasper |
20d7059b-da44-4cc1-99ec-7099b4397d56 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the CORD-19 dataset?\n\nIntroduction\nCoronavirus disease 2019 (COVID-19) is an infectious disease that has affected more than one million individuals all over the world and caused more than 55,000 deaths, as of April 3 in 202... | [
"which contains over 45,000 scholarly articles, including over 33,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses"
] | 2,991 | qasper |
21aa9471-7442-453b-8505-45c5b09d4179 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What sentiment analysis dataset is used?\n\nIntroduction\nThere have been many implementations of the word2vec model in either of the two architectures it provides: continuous skipgram and CBoW (BIBREF0). Similar distributed models of... | [
"IMDb dataset of movie reviews"
] | 3,343 | qasper |
29b92f1b-6f33-4939-a3b8-581f5668ba1c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they analyze specific derogatory words?\n\nKeywords:\ncomputational sociolinguistics, dehumanization, lexical variation, language change, media, New York Times, LGBTQ\nWarning: this paper contains material that some may find offens... | [
"Yes"
] | 17,774 | qasper |
46841072-7012-4bd8-8546-a4c295790b72 | [{"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... | [
"majority of questions that our system could not answer so far are in fact answerable"
] | 5,274 | qasper |
6c43df85-f123-4d64-90ee-9725310cf49e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what pretrained word embeddings were used?\n\nIntroduction\nTwitter, a micro-blogging and social networking site has emerged as a platform where people express themselves and react to events in real-time. It is estimated that nearly 5... | [
"Pretrained word embeddings were not used"
] | 2,365 | qasper |
6c78e057-bf18-4822-974e-e1b219de68d8 | [{"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... | [
"BLEU-1/4 and ROUGE-L, likelihood of generated recipes using identical input specifications but conditioned on ten different user profiles, user matching accuracy (UMA), Mean Reciprocal Rank (MRR), neural scoring model from BIBREF33 to measure recipe-level coherence"
] | 3,949 | qasper |
751e5e81-2631-4a67-aaa8-80888a117e12 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How they utilize LDA and Gibbs sampling to evaluate ISWC and WWW publications?\n\nIntroduction\nToday, Internet is one of the widest available media worldwide. It has essentially become a huge hit of data that has the potential to ser... | [
"discover the trends of the topics and find relationship between LDA topics and paper features and generate trust tags, learn a LDA model with 100 topics; $\\alpha =0.01$, $\\beta = 0.01$ and using Gibbs sampling as a parameter estimation"
] | 6,380 | qasper |
7b8f8157-b4fb-4522-873e-8a30537977b5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many sentences does the dataset contain?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"ORGANIZATION\" a... | [
"3606"
] | 4,287 | qasper |
82b79007-8ebf-4d38-9943-4671cea8eb3c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is Augmented LibriSpeech dataset?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automatic s... | [
"Unanswerable"
] | 3,600 | qasper |
8df6e88e-e67d-4dee-a5b2-61c211eb704e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they collected the two datasets?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/ Deep neural networks have been wi... | [
"No"
] | 5,896 | qasper |
96829d58-7b7f-4af1-869e-4af2b16972f0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which existing models are evaluated?\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 N... | [
"Show&Tell and LRCN1u"
] | 4,578 | qasper |
a29c2cf2-967a-49eb-a42b-7b2a81cf4dc8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what pretrained word embeddings were used?\n\nIntroduction\nTwitter, a micro-blogging and social networking site has emerged as a platform where people express themselves and react to events in real-time. It is estimated that nearly 5... | [
"GloVe, Edinburgh embeddings BIBREF14, Emoji embeddings BIBREF16"
] | 2,365 | qasper |
b53a843b-cead-46d0-bbd9-e060d4706bea | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used to evaluate this paper?\n\nIntroduction\nKnowledge graphs have been proved to benefit many artificial intelligence applications, such as relation extraction, question answering and so on. A knowledge graph consi... | [
"WordNet BIBREF0, Freebase BIBREF1, WN18 (a subset of WordNet) BIBREF24 , FB15K (a subset of Freebase) BIBREF2"
] | 5,215 | qasper |
b5d9359c-54a3-423f-bc38-300adc158085 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they extend LAMA evaluation framework to focus on negation?\n\nIntroduction\nPretrained language models like Transformer-XL BIBREF1, ELMo BIBREF2 and BERT BIBREF3 have emerged as universal tools that capture a diverse range of... | [
"Create the negated LAMA dataset and query the pretrained language models with both original LAMA and negated LAMA statements and compare their predictions."
] | 1,840 | qasper |
b6059724-deb8-4ae1-8436-92ce926e7d30 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the clinical datasets used in the paper?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data sharing and processin... | [
"MEDDOCAN, NUBes-PHI"
] | 6,153 | qasper |
b842b099-65f3-412a-abd4-c1845a1759c7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the degree of dimension reduction of the efficient aggregation method?\n\nIntroduction\nVector-based semantic mapping models are used to represent textual structures (words, phrases, and documents) as high-dimensional meaning ... | [
"The number of dimensions can be reduced by up to 212 times."
] | 5,390 | qasper |
bac06bc2-cdb3-4ebd-85ef-81527a9cbcb1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they introduce errors in the data or does the data already contain them?\n\nIntroduction\nSequence-to-sequence (seq2seq) transformations have recently proven to be a successful framework for several natural language processing task... | [
" all three languages have error-corrected corpora for testing purposes"
] | 6,342 | qasper |
d0fe892b-946b-4eab-b1d7-fa70df178c92 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What parallel corpus did they use?\n\nIntroduction\nRecently, neural machine translation (NMT) has gained popularity in the field of machine translation. The conventional encoder-decoder NMT proposed by Cho2014 uses two recurrent neur... | [
"Asian Scientific Paper Excerpt Corpus (ASPEC) BIBREF0, NTCIR PatentMT Parallel Corpus BIBREF1"
] | 3,066 | qasper |
d4ae525c-ae06-4432-b021-37905d7568b0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What sentiment analysis dataset is used?\n\nIntroduction\nThere have been many implementations of the word2vec model in either of the two architectures it provides: continuous skipgram and CBoW (BIBREF0). Similar distributed models of... | [
"IMDb"
] | 3,343 | qasper |
d67ccfe2-d469-4122-ad25-16505e097b05 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the previous state of the art?\n\nIntroduction\nModern Standard Arabic (MSA) and Classical Arabic (CA) have two types of vowels, namely long vowels, which are explicitly written, and short vowels, aka diacritics, which are ty... | [
"Farasa, RDI"
] | 7,074 | qasper |
ea67b470-dfc0-4f1e-b578-94359ecc91d8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which existing strategies are compared?\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 gen... | [
"Unanswerable"
] | 3,223 | qasper |
ea7939e7-9186-4fc7-b619-243284b06c5f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\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 behavio... | [
"Unanswerable"
] | 3,191 | qasper |
f8c6b72c-6a64-4d07-8981-39cbb10997d6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What labels does the dataset have?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribute s... | [
"Ekman’s six basic emotions, neutral"
] | 4,511 | qasper |
fff9b32c-2e5a-43f3-8ecf-e8f7f1978656 | [{"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... | [
"answer questions by obtaining information from KB tuples "
] | 6,737 | qasper |
001daabf-ddf4-4efc-9f4f-245272f3d362 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics do they use?\n\nIntroduction\nSocial media is now becoming an important real-time information source, especially during natural disasters and emergencies. It is now very common for traditional news media to fre... | [
"BLEU-1, Meteor , Rouge-L "
] | 4,645 | qasper |
049c5da2-715a-4e0e-b722-35ca2e16e375 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets are used?\n\nIntroduction\nBack to 42 BC, the philosopher Cicero has raised the issue that although there were many Oratory classes, there were none for Conversational skills BIBREF0 . He highlighted how important they w... | [
"Custom dataset with user questions; set of documents, twitter posts and news articles, all related to finance."
] | 17,788 | qasper |
07c3cc6c-4458-4c04-9e77-835c823d5a8e | [{"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... | [
"by crawling"
] | 6,082 | qasper |
1c2c3a83-8717-4534-8359-11ad4c40ca25 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they employ their indexing-based method to create a sample of a QA Wikipedia dataset?\n\nIntroduction\nQuestion answering (QA) has been a blooming research field for the last decade. Selection-based QA implies a family of tasks tha... | [
"Yes"
] | 2,612 | qasper |
29d986bc-2534-4d72-aa3f-e75e31811685 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the state of the art methods?\n\nIntroduction\nGrammar induction is the task of inducing hierarchical syntactic structure from data. Statistical approaches to grammar induction require specifying a probabilistic grammar (e.g.... | [
"Unanswerable"
] | 3,612 | qasper |
2a13fdd0-b7af-4d82-a944-4d958a83c405 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they demonstrate that this type of EEG has discriminative information about the intended articulatory movements responsible for speech?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of th... | [
"we plot T-distributed Stochastic Neighbor Embedding (tSNE) corresponding to INLINEFORM0 and V/C classification tasks in Fig. FIGREF8 ."
] | 3,296 | qasper |
36908432-43db-4942-a861-369e566736c2 | [{"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 |
5cdde4dc-ec11-4665-a867-eae82b64097a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how was the speech collected?\n\nIntroduction\nNowadays deep learning techniques outperform the other conventional methods in most of the speech-related tasks. Training robust deep neural networks for each task depends on the availabi... | [
"The speech was collected from respondents using an android application."
] | 5,097 | qasper |
5ef9419b-8f3e-4cca-ab6e-f9ad2506ee12 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the organic and inorganic ways to show political affiliation through profile changes?\n\nIntroduction\nUser profiles on social media platforms serve as a virtual introduction of the users. People often maintain their online p... | [
"Mentioning of political parties names and political twitter handles is the organic way to show political affiliation; adding Chowkidar or its variants to the profile is the inorganic way."
] | 6,816 | qasper |
65bae693-3828-4f27-8433-00b64e04e88e | [{"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 |
68c66b2b-4470-4634-ac5e-0dfeadd0e2f0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the algorithm improve on the state-of-the-art methods?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece ... | [
"From all reported results proposed method (NB+Lex) shows best accuracy on all 3 datasets - some models are not evaluated and not available in literature."
] | 2,614 | qasper |
6d1dc42e-c45a-4a53-9eec-04ed3a853668 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the datasets used for evaluation?\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 entit... | [
"CNN/DailyMail news highlights, New York Times Annotated Corpus, XSum"
] | 6,516 | qasper |
876a9585-626d-40fd-92b0-39766fa83abb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics were used for the summarization task?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their wor... | [
"ROUGE BIBREF22 unigram score"
] | 4,198 | qasper |
95cd3232-aff0-4c5b-89f4-3d2576fd87a7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language are the reviews in?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data h... | [
"English"
] | 4,701 | qasper |
9a4d4bd7-6317-42dd-902f-362e1c9066b0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use datasets with transcribed text or do they determine text from the audio?\n\nIntroduction\nRecently, deep learning algorithms have successfully addressed problems in various fields, such as image classification, machine tra... | [
"They use text transcription."
] | 4,320 | qasper |
9b11f01c-4d8f-4b4b-88bd-095596c0e492 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is car-speak language collection of abstract features that classifier is later trained on?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, ... | [
"No"
] | 2,212 | qasper |
a203205a-4c9a-455b-9932-c27880adddc0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What functionality does Macaw provide?\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 th... | [
"Co-Reference Resolution, Query Generation, Retrieval Model, Result Generation"
] | 2,270 | qasper |
a7d403d3-c8ac-489d-9d93-b5c855d8a8d6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much more does PARENT correlate with human judgements in comparison to other text generation metrics?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 ,... | [
"Best proposed metric has average correlation with human judgement of 0.913 and 0.846 compared to best compared metrics result of 0.758 and 0.829 on WikiBio and WebNLG challenge."
] | 5,094 | qasper |
af05ab20-3373-4a32-b5fb-9f13059803d4 | [{"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... | [
"A semi-character based RNN (ScRNN) treats the first and last characters individually, and is agnostic to the ordering of the internal characters"
] | 5,903 | qasper |
bbe8020c-889b-4586-a27d-e3cbae91ada2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what was the baseline?\n\nIntroduction\nNeural machine translation (NMT) BIBREF0 , BIBREF1 , BIBREF2 has enabled end-to-end training of a translation system without needing to deal with word alignments, translation rules, and complica... | [
"M2M Transformer"
] | 6,552 | qasper |
c2517460-84f4-4f25-b615-dcbc86178fe6 | [{"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"
] | 3,222 | qasper |
c2768c8b-4e7c-4799-9687-b79266c2ea1b | [{"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 |
de6431cd-3db4-473a-96e0-84a5ad084d74 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which eight NER tasks did they evaluate on?\n\nIntroduction\nPretrained Language Models (PTLMs) such as BERT BIBREF1 have spearheaded advances on many NLP tasks. Usually, PTLMs are pretrained on unlabeled general-domain and/or mixed-d... | [
"BC5CDR-disease, NCBI-disease, BC5CDR-chem, BC4CHEMD, BC2GM, JNLPBA, LINNAEUS, Species-800"
] | 5,064 | qasper |
dfeef3bf-29ba-4cf8-83c4-5a6b1746dce5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which algorithm was the highest performer?\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. ... | [
"A hybrid model consisting of best performing popularity-based approach with the best similarity-based approach"
] | 4,425 | qasper |
f6f23772-f968-4e4a-9257-a1ee71f08656 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the state-of-the-art model for the task?\n\nIntroduction\nTable-to-text generation is an important and challenging task in natural language processing, which aims to produce the summarization of numerical table BIBREF0, BIBREF... | [
"OpATT BIBREF6, Neural Content Planning with conditional copy (NCP+CC) BIBREF4"
] | 6,986 | qasper |
ff017769-8798-478f-a0b1-94c17bded813 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the common belief that this paper refutes? (c.f. 'contrary to the common belief, ROUGE is not much [sic] reliable'\n\nIntroduction\nAutomatic text summarization has been an active research area in natural language processing f... | [
"correlations between Rouge and the Pyramid scores are weak, which challenges its effectiveness for scientific summarization"
] | 6,289 | qasper |
ff74bcec-f463-4cff-94ea-2ae2d9c377ce | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What methods were used for sentence classification?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their workforce. Th... | [
"Logistic Regression, Multinomial Naive Bayes, Random Forest, AdaBoost, Linear SVM, SVM with ADWSK, Pattern-based approach"
] | 4,195 | qasper |
0c2d2c1e-f782-437c-b5e0-cb03d8e24590 | [{"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 |
0d239ff7-cb9d-4843-aafe-45befc847b5e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What activation function do they use in their model?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is th... | [
"relu, selu, tanh"
] | 2,885 | qasper |
0eae9df7-ab06-4860-a103-2b8f5ee80e66 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments are proposed to test that upper layers produce context-specific embeddings?\n\nIntroduction\nThe application of deep learning methods to NLP is made possible by representing words as vectors in a low-dimensional conti... | [
"They plot the average cosine similarity between uniformly random words increases exponentially from layers 8 through 12. \nThey plot the average self-similarity of uniformly randomly sampled words in each layer of BERT, ELMo, and GPT-2 and shown that the higher layer produces more context-specific embeddings.\nTh... | 6,140 | qasper |
145e9e49-6d2c-4606-a9cb-2c4c990425d9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they obtain the dataset?\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 ... | [
"For the non-factual accounts, we rely on a list of 180 Twitter accounts from BIBREF1, we use a list with another 32 Twitter accounts from BIBREF19 that are considered trustworthy"
] | 2,882 | qasper |
1553088e-8a75-42c2-80ef-090339841a21 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what methods were used to reduce data sparsity effects?\n\nIntroduction\nNeural machine translation (NMT) BIBREF0 , BIBREF1 is widely applied for machine translation (MT) in recent years and focuses on popular language pairs such as E... | [
"Back Translation, Mix-Source Approach"
] | 5,567 | qasper |
16e6c9f5-c5e6-47be-8a61-d328b1dd8d71 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the qualitative experiments performed on benchmark datasets?\n\nIntroduction\nLanguage modelling in its inception had one-hot vector encoding of words. However, it captures only alphabetic ordering but not the word semantic s... | [
"Spearman correlation values of GM_KL model evaluated on the benchmark word similarity datasets.\nEvaluation results of GM_KL model on the entailment datasets such as entailment pairs dataset created from WordNet, crowdsourced dataset of 79 semantic relations labelled as entailed or not and annotated distributional... | 3,407 | qasper |
1c3b929c-4fcc-499e-aa40-12f8853cfbbc | [{"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 , Swedish"
] | 3,758 | qasper |
3373d1c3-49f4-443f-9bc6-511e6bfae5e2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what topics did they label?\n\nIntroduction\nSummarization of patient information is essential to the practice of medicine. Clinicians must synthesize information from diverse data sources to communicate with colleagues and provide co... | [
"Demographics, Diagnosis History, Medication History, Procedure History, Symptoms, Labs, Procedures, Treatments, Hospital movements, and others"
] | 3,945 | qasper |
33cc4da8-a581-4bfc-b26b-579c9184a887 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What cyberbulling topics did they address?\n\nIntroduction\nCyberbullying has been defined by the National Crime Prevention Council as the use of the Internet, cell phones or other devices to send or post text or images intended to hu... | [
"personal attack, racism, and sexism"
] | 4,318 | qasper |
346de8e0-97d4-477e-b1f3-697f21a490b8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors train a Naive Bayes classifier on 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\",... | [
"No"
] | 4,293 | qasper |
3671a94e-b23b-4917-8abc-f2d6c667c941 | [{"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... | [
"offensive (OFF) and non-offensive (NOT), targeted (TIN) and untargeted (INT) insults, targets of insults and threats as individual (IND), group (GRP), and other (OTH)"
] | 3,085 | qasper |
3686ba59-3347-4db3-b412-c35af135c048 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance improvement of the grapheme-level representation model over the character-level model?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into spe... | [
"BiLSTM+CNN(grapheme-level) which turns out to be performing on par with BiLSTM+CNN(character-level) under the same configuration"
] | 4,297 | qasper |
37c68aee-0d21-45d6-a320-73d9131dd4fa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nEvent detection on microblogging platforms such as Twitter aims to detect events preemptively. A main task in event detection is detecting events of predetermined types BIB... | [
"Yes"
] | 6,675 | qasper |
395becfe-99ba-4ae3-baaf-b04d39f9689b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they try to use byte-pair encoding representations?\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\", \"ORGANI... | [
"No"
] | 4,290 | qasper |
3e73c012-7d20-40e0-94f4-6eb1711e4d1b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nAutomatic summarization has enjoyed wide popularity in natural language processing due to its potential for various information access applications. Examples include tools which aid users navig... | [
"Answer with content missing: (Experimental Setup missing subsections)\nTo be selected: We compared REFRESH against a baseline which simply selects the first m leading sentences from each document (LEAD) and two neural models similar to ours (see left block in Figure 1), both trained with cross-entropy loss.\nAnswe... | 3,864 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.