uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
98083321-9141-4b88-8229-1af06dddde93 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of BERT on the task?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data sharing and processing cap... | [
"BERT remains only 0.3 F1-score points behind, and would have achieved the second position among all the MEDDOCAN shared task competitors. Taking into account that only 3% of the gold labels remain incorrectly annotated, Table "
] | 6,154 | qasper |
9d72abea-0474-4f06-be25-cf109d66c6c3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What neural network modules are included in NeuronBlocks?\n\nIntroduction\nDeep Neural Networks (DNN) have been widely employed in industry for solving various Natural Language Processing (NLP) tasks, such as text classification, sequ... | [
"Embedding Layer, Neural Network Layers, Loss Function, Metrics"
] | 2,357 | qasper |
a41aceb6-9781-4cc8-b8d5-2c7ba4dcc565 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where does the data come from?\n\nIntroduction\nTask-oriented dialog systems have become ubiquitous, providing a means for billions of people to interact with computers using natural language. Moreover, the recent influx of platforms ... | [
"For ins scope data collection:crowd workers which provide questions and commands related to topic domains and additional data the rephrase and scenario crowdsourcing tasks proposed by BIBREF2 is used. \nFor out of scope data collection: from workers mistakes-queries written for one of the 150 intents that did not... | 3,155 | qasper |
a515c200-5ca1-4e44-b8a7-879991426aec | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which syntactic features are obtained automatically on downstream task data?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs) d... | [
"token-level chunk label embeddings, chunk boundary information is passed into the task model via BIOUL encoding of the labels"
] | 3,685 | qasper |
b127e9f1-22d2-4d84-9ce1-fca7a00d7e5f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What BERT model do they test?\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 natural language infere... | [
"BERTbase"
] | 5,592 | qasper |
d2610996-7c10-4880-a4be-b6b71a62a7b7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why challenges does word segmentation in Vietnamese pose?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural language processing BIBREF0 ... | [
"Acquire very large Vietnamese corpus and build a classifier with it, design a develop a big data warehouse and analytic framework, build a system to incrementally learn new corpora and interactively process feedback."
] | 4,683 | qasper |
e4b34076-64b2-4942-aa04-f536472b4d0c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How they extract \"structured answer-relevant relation\"?\n\nIntroduction\nQuestion Generation (QG) is the task of automatically creating questions from a range of inputs, such as natural language text BIBREF0, knowledge base BIBREF1 ... | [
"off-the-shelf toolbox of OpenIE"
] | 5,607 | qasper |
e5b247c6-b58e-4311-8e85-9b36892055e7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What novel PMI variants are introduced?\n\nIntroduction\nDense word vectors (or embeddings) are a key component in modern NLP architectures for tasks such as sentiment analysis, parsing, and machine translation. These vectors can be l... | [
"clipped PMI; NNEGPMI"
] | 3,413 | qasper |
e5e98cba-ed82-442a-aa2f-f8bf548e44ac | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used for this study?\n\nIntroduction\nIn recent years, there has been a movement to leverage social medial data to detect, estimate, and track the change in prevalence of disease. For example, eating disorders in Spani... | [
"an existing, annotated Twitter dataset that was constructed based on a hierarchical model of depression-related symptoms BIBREF12 , BIBREF13"
] | 2,800 | qasper |
f5a701d1-1af0-4615-9d5d-7e007ea3c157 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets were used?\n\nIntroduction\nIn the field of natural language processing (NLP), the most prevalent neural approach to obtaining sentence representations is to use recurrent neural networks (RNNs), where words in a senten... | [
"SNLI BIBREF22 and MultiNLI BIBREF23 datasets, Quora Question Pairs dataset BIBREF24, Stanford Sentiment Treebank (SST) BIBREF25"
] | 4,498 | qasper |
fa8cf846-ee1d-44ca-ace6-aec23d3c840f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what corpus is used to learn behavior?\n\nIntroduction\nSpoken Dialogue Systems (SDS) allow human-computer interaction using natural speech. Task-oriented dialogue systems, the focus of this work, help users achieve goals such as find... | [
"DSTC2"
] | 6,341 | qasper |
ffc6e205-d8eb-40f8-b10a-048e1336d6d4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What do they mean by global and local context?\n\nIntroduction\nSingle-document summarization is the task of generating a short summary for a given document. Ideally, the generated summaries should be fluent and coherent, and should f... | [
"global (the whole document), local context (e.g., the section/topic)"
] | 5,768 | qasper |
1a7370e2-5bc9-4ae5-a664-6e6666610054 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset has been used in this work?\n\nIntroduction\nText classification has become an indispensable task due to the rapid growth in the number of texts in digital form available online. It aims to classify different texts, also... | [
"Reuters-8 dataset without stop words"
] | 7,839 | qasper |
1a8f8d11-bd29-44aa-a24e-1b5c549af2c2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What BERT model do they test?\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 natural language infere... | [
"BERTbase"
] | 5,592 | qasper |
1f9bd7ce-901f-4f2b-99a3-602a8f65dedd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the source of their dataset?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"ORGANIZATION\" and other... | [
"daily newspaper of the year 2015-2016"
] | 4,287 | qasper |
21646e94-b77d-4cc6-b66e-000472541465 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the performance of multilingual BERT?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding systems for political science, opinio... | [
"BERT had 76.6 F1 macro score on x-stance dataset."
] | 5,000 | qasper |
22b972d7-a663-4b88-b73c-7b827dfa1495 | [{"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 |
2f1ad82a-439d-41a0-8b81-1883bf2d1913 | [{"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... | [
"Unanswerable"
] | 6,675 | qasper |
2fa1a065-0cb5-4a63-b4cc-c547bf12d2b8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the model architecture used?\n\nIntroduction\nWhat would be possible if a person had an oracle that could immediately provide the answer to any question about the visual world? Sight-impaired users could quickly and reliably f... | [
"LSTM to encode the question, VGG16 to extract visual features. The outputs of LSTM and VGG16 are multiplied element-wise and sent to a softmax layer."
] | 5,050 | qasper |
307ed994-c4f1-4577-a85a-8f8ab6fdd299 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do co-purchase patterns vary across seasons?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semantic structure in languag... | [
"Unanswerable"
] | 4,296 | qasper |
3c13e258-c5fa-4ce7-93cd-e767cdf7ce2d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metric is used to evaluate PolyReponse system?\n\nIntroduction and Background\nTask-oriented dialogue systems are primarily designed to search and interact with large databases which contain information pertaining to a certain di... | [
"Unanswerable"
] | 3,848 | qasper |
4390414b-076b-4a3c-a560-b740967535de | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they encourage understanding of literature as part of their objective function?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic... | [
"They group the existing works in terms of the objective function they optimize - within-tweet relationships, inter-tweet relationships, autoencoder, and weak supervision."
] | 2,514 | qasper |
47cb860e-6e2a-4373-a594-ded2373bab9a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the state of the art on WSJ?\n\nIntroduction\nRecent work on convolutional neural network architectures showed that they are competitive with recurrent architectures even on tasks where modeling long-range dependencies is crit... | [
"HMM-based system"
] | 2,774 | qasper |
55cb657c-6bd0-4394-b855-32af43c8f774 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they calculate a static embedding for each word?\n\nIntroduction\nThe application of deep learning methods to NLP is made possible by representing words as vectors in a low-dimensional continuous space. Traditionally, these wor... | [
"They use the first principal component of a word's contextualized representation in a given layer as its static embedding."
] | 6,137 | qasper |
5d24000c-7c98-44ac-aec1-ab78e20a78ae | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the previous state of the art?\n\nIntroduction\nOther than encoder-only pretrained transformer architectures BIBREF2, BIBREF3, BIBREF4, encoder–decoder style pretrained transformers BIBREF0, BIBREF5 have been proven to be effe... | [
"RoBERTa"
] | 1,830 | qasper |
64cb3e11-7da6-4c2e-9c21-cee1ec97641f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What model did they use for their system?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friends a... | [
"AllWords model by counting the frequencies of all the remaining words and training a multinomial Naive Bayes classifier"
] | 5,299 | qasper |
6de2c923-133a-4b65-b65c-74a9a0cf1de4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the different variations of the attention-based approach which are examined?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically wom... | [
"classic RNN model, avgRNN model, attentionRNN model and multiattention RNN model with and without a projected layer"
] | 3,872 | qasper |
713472cf-b19b-4f43-a022-8dfc3f52f4e1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what competitive results did they obtain?\n\nIntroduction\nConventional automatic speech recognition (ASR) systems typically consist of several independently learned components: an acoustic model to predict context-dependent sub-phone... | [
"In case of read speech datasets, their best model got the highest nov93 score of 16.1 and the highest nov92 score of 13.3.\nIn case of Conversational Speech, their best model got the highest SWB of 8.3 and the highest CHM of 19.3. "
] | 2,755 | qasper |
77cd98ca-39d2-418e-8bc8-6aea1fe75e64 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What data was presented to the subjects to elicit event-related responses?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIB... | [
"KARA ONE BIBREF17 , composed of multimodal data for stimulus-based, imagined and articulated speech state corresponding to 7 phonemic/syllabic ( /iy/, /piy/, /tiy/, /diy/, /uw/, /m/, /n/ ) as well as 4 words(pat, pot, knew and gnaw)"
] | 3,287 | qasper |
7a2d10ae-3414-429f-9ace-8061bab18f58 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors also try the model on other datasets?\n\nIntroduction\nSingle-relation factoid questions are the most common form of questions found in search query logs and community question answering websites BIBREF1 , BIBREF2 . A k... | [
"No"
] | 5,342 | qasper |
7e934da3-b3b9-4a29-9c04-b72974fe443f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages fo... | [
"Yes"
] | 10,239 | qasper |
8cb9d2df-086b-4b6d-b416-ccd62c80ee91 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of sentences were read?\n\nIntroduction\nHow humans process language has become increasingly relevant in natural language processing since physiological data during language understanding is more accessible and recorded with... | [
"seven of the originally defined relation types: political_affiliation, education, founder, wife/husband, job_title, nationality, and employer"
] | 4,710 | qasper |
94e05201-cb09-4ca5-ab7e-d3546bf0e375 | [{"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... | [
"A task for seq2seq model pra-training that recovers a masked document to its original form."
] | 6,833 | qasper |
a402aff5-890e-4012-955b-ae8438be3f6c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On what Text-Based Games are experiments performed?\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 BIBREF2. T... | [
"CoinCollector, CookingWorld"
] | 6,937 | qasper |
a940e086-edcd-4575-9a6b-e7d6bedb9bbe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many layers does their model have?\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 fo... | [
"Unanswerable"
] | 2,883 | qasper |
d28510a0-9a46-4b6d-8d3e-f6368a6719a5 | [{"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, which is not of high quality"
] | 3,617 | qasper |
d3a4e71e-9733-4340-998e-745325d04e77 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What models are used in the experiment?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most comm... | [
"linear SVM, bidirectional Long Short-Term-Memory (BiLSTM), Convolutional Neural Network (CNN)"
] | 3,085 | qasper |
d4cc6b5c-d64e-4200-88c0-e0b3451f621a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which annotated corpus did they use?\n\nIntroduction\nWriting errors can occur in many different forms – from relatively simple punctuation and determiner errors, to mistakes including word tense and form, incorrect collocations and e... | [
" FCE test data (41K tokens) and the two alternative annotations of the CoNLL 2014 Shared Task dataset (30K tokens) "
] | 2,711 | qasper |
077a8dc2-6984-479a-baea-381e129d6c67 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets are used for evaluation?\n\nIntroduction\nUnderstanding what a question is asking is one of the first steps that humans use to work towards an answer. In the context of question answering, question classification allows... | [
"ARC , TREC, GARD , MLBioMedLAT "
] | 8,027 | qasper |
0b00214a-2e1d-4f9c-bbe5-59b3271cae5d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used for this work?\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 very common... | [
"The dataset from the SociaL Media And Harassment Competition of the ECML PKDD 2019 Conference."
] | 3,866 | qasper |
3af16e20-2396-40ff-8340-e85c02dd7e53 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is their system's absolute accuracy?\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 ess... | [
"59.4% on wikipedia dataset, 93.4% on peer-reviewed archive AI papers, 77.1% on peer-reviewed archive Computation and Language papers, and 79.9% on peer-reviewed archive Machine Learning papers"
] | 5,707 | qasper |
4223ec43-913d-495c-9fce-6077a5e1dd6e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What they use in their propsoed framework?\n\nIntroduction\nKnowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 . For an i... | [
"break the relation names into word sequences, relation-level and word-level relation representations, bidirectional LSTMs (BiLSTMs), residual learning method"
] | 6,738 | qasper |
55b230f4-8f32-4cb3-bba4-ecf25780a95a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is specific to multi-granularity and multi-tasking neural arhiteture design?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social med... | [
"An output layer for each task"
] | 2,447 | qasper |
678c2e52-33b2-4a4e-ad56-c06859892484 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which architecture do they use for the encoder and decoder?\n\nIntroduction\nConventional large-vocabulary continuous speech recognition (LVCSR) systems typically perform multi-level pattern recognition tasks that map the acoustic spe... | [
"In encoder they use convolutional, NIN and bidirectional LSTM layers and in decoder they use unidirectional LSTM "
] | 3,657 | qasper |
6bda5845-4414-4872-ab20-544e1eeb4cdc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the real-life dataset?\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. The PA proc... | [
"26972 sentences"
] | 4,197 | qasper |
7928015c-567d-4a9c-aae8-d7d6c50f4b2b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they test both skipgram and c-bow?\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 wo... | [
"Yes"
] | 3,347 | qasper |
7d24924d-e081-4ee8-988b-69a8a20cb71e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics are looked at for classification tasks?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their w... | [
"Precision, Recall, F-measure, accuracy"
] | 4,197 | qasper |
81b75e5f-8309-4341-a0cb-2b7bdb625a18 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are examples of these artificats?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect and annotate data in multipl... | [
"hypothesis-only baseline performs better than chance due to cues on their lexical choice and sentence length, NLI models tend to predict entailment for sentence pairs with a high lexical overlap"
] | 5,515 | qasper |
81fb0a73-f09f-42bb-b5e3-d8e8c840909d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they build a model to automatically detect demographic, lingustic or psycological dimensons of people?\n\nIntroduction\nBlogging gained momentum in 1999 and became especially popular after the launch of freely available, hosted pla... | [
"No"
] | 1,948 | qasper |
83ce7af1-5d57-4132-b382-a2b1067ab6c9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why challenges does word segmentation in Vietnamese pose?\n\nIntroduction\nLexical analysis, syntactic analysis, semantic analysis, disclosure analysis and pragmatic analysis are five main steps in natural language processing BIBREF0 ... | [
"to acquire very large Vietnamese corpus and to use them in building a classifier, design and development of big data warehouse and analytic framework for Vietnamese documents, to building a system, which is able to incrementally learn new corpora and interactively process feedback"
] | 4,683 | qasper |
97f8339e-ed26-4a71-94ab-8dbd22a98469 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big are improvements of small-scale unbalanced datasets when sentence representation is enhanced with topic information?\n\nIntroduction\nMedical text mining is an exciting area and is becoming attractive to natural language proce... | [
"it has 0.024 improvement in accuracy comparing to ELMO Only and 0.006 improvement in F1 score comparing to ELMO Only too"
] | 4,075 | qasper |
a444c188-4ed9-49e1-9922-79455ea26ea8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the source of the data?\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 availa... | [
"Android application"
] | 5,099 | qasper |
b4c2c762-66a4-4846-bb8e-a2da4b5057ba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the benchmark attacking methods?\n\nIntroduction\nAdversarial examples, a term introduced in BIBREF0, are inputs transformed by small perturbations that machine learning models consistently misclassify. The experiments are co... | [
"FGM, FGVM, DeepFool, HotFlip, TYC"
] | 6,095 | qasper |
ba266528-d2c6-4d29-bc38-aff1e38e80ff | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are humans and machine learning systems fooled by the same kinds of illusions?\n\nIntroduction\nA growing body of work on adversarial examples has identified that for machine-learning (ML) systems that operate on high-dimensional data... | [
"Unanswerable"
] | 4,437 | qasper |
bc898048-ae91-49d0-8162-58b331ede5a9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use attention?\n\nBackground\nTeaching machine to read and comprehend a given passage/paragraph and answer its corresponding questions is a challenging task. It is also one of the long-term goals of natural language understand... | [
"Yes"
] | 2,436 | qasper |
bdf33c6d-d765-4bb2-a1b5-e4c15d2d0725 | [{"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 ... | [
"Answer with content missing: (Whole Method and Results sections) The primary dataset we use is the ERP data collected and computed by Frank et al. (2015), and we also use behavioral data (eye-tracking data and self-paced reading times) from Frank et al. (2013) which were collected on the same set of 205 sentences.... | 2,364 | qasper |
c4451cc1-5da8-4fe7-8f33-5e0bf2c60cd5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method's improvements of F1 w.r.t. baseline BERT tagger for Chinese POS datasets?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gi... | [
"+1.86 in terms of F1 score on CTB5, +1.80 on CTB6, +2.19 on UD1.4"
] | 5,651 | qasper |
cf7e8678-f032-4322-bcf4-eab66418871e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the five different binary classification tasks?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIBREF0 , BIBREF1 . I... | [
"presence/absence of consonants, presence/absence of phonemic nasal, presence/absence of bilabial, presence/absence of high-front vowels, and presence/absence of high-back vowels"
] | 3,282 | qasper |
e154e771-99d3-4ebf-8bbb-e7972f9c3212 | [{"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 |
e1ace6bd-31bc-458b-9965-27f7e5a13a23 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what state of the art methods did they compare with?\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 ... | [
"OpenNMT, PBMT-R, Hybrid, SBMT-SARI, Dress"
] | 3,189 | qasper |
f131b9cb-e459-49f8-a546-bc761f4cb717 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are absent from MRC gold standards that can result in potential lexical ambiguity?\n\nIntroduction\nThere is a recent spark of interest in the task of Question Answering (QA) over unstructured textual data, also referred... | [
"Restrictivity , Factivity , Coreference "
] | 6,569 | qasper |
f73f0532-4d51-43aa-b09e-75268a00c95d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of questions are present in the dataset?\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 ... | [
"These 8 tasks require different competencies and a different level of understanding of the document to be well answered"
] | 4,704 | qasper |
f92b7f2d-92c8-4edf-bc93-a565562dd75f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which race and gender are given higher sentiment intensity predictions?\n\nIntroduction\n[0]leftmargin=* [0]leftmargin=*\nAutomatic systems have had a significant and beneficial impact on all walks of human life. So much so that it is... | [
" the number of systems consistently giving higher scores to sentences with female noun phrases, higher scores to sentences with African American names on the tasks of anger, fear, and sadness, joy and valence tasks, most submissions tended to assign higher scores to sentences with European American names"
] | 6,027 | qasper |
fa5e1ca9-5a19-4ac7-bfe6-896ce3f3fe77 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they incoprorate WordNet into the model?\n\nIntroduction\nWord Sense Disambiguation (WSD) is a fundamental task and long-standing challenge in Natural Language Processing (NLP), which aims to find the exact sense of an ambiguous wo... | [
"construct context-gloss pairs from all possible senses of the target word in WordNet, thus treating WSD task as a sentence-pair classification problem"
] | 3,006 | qasper |
fc46a2d4-064c-4d10-ba2d-1459ae37c4ef | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which publicly available datasets are used?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interact... | [
"Waseem and Hovey BIBREF5, Davidson et al. BIBREF9"
] | 5,697 | qasper |
08d1bc1a-4083-4497-9458-e6b9907529fd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building blocks in the course of algor... | [
"Yes"
] | 8,083 | qasper |
194eab02-553b-41ce-87c0-369ed9166c69 | [{"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... | [
"CCG Supertagging CCGBank , PTB part-of-speech tagging, EWT part-of-speech tagging,\nChunking, Named Entity Recognition, Semantic Tagging, Grammar Error Detection, Preposition Supersense Role, Preposition Supersense Function, Event Factuality Detection"
] | 3,681 | qasper |
1cc8362c-396c-4da9-a769-87a92d9dc1d4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"where did they obtain the annotated clinical notes from?\n\nIntroduction\nMedical search engines are an essential component for many online medical applications, such as online diagnosis systems and medical document databases. A typic... | [
"clinical notes from the CE task in 2010 i2b2/VA "
] | 4,888 | qasper |
225055cb-9de0-4565-8bbc-f16bbce68ff5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is jiant compatible with models in any programming language?\n\nIntroduction\nThis paper introduces jiant, an open source toolkit that allows researchers to quickly experiment on a wide array of NLU tasks, using state-of-the-art NLP m... | [
"Unanswerable"
] | 3,368 | qasper |
331edc14-1228-4314-aae1-a04dfae427ba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What language model architectures are used?\n\nIntroduction\nPre-training of language models has been shown to provide large improvements for a range of language understanding tasks BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . The key idea... | [
"uni-directional model to augment the decoder"
] | 2,667 | qasper |
339da05f-cbb9-4321-b9b9-5dd1f177d45b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are used to represent the salience and relative authority of entities?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into ... | [
"Salience features positional features, occurrence frequency and the internal POS structure of the entity and the sentence it occurs in.\nThe relative authority of entity features: comparative relevance of the news article to the different entities occurring in it."
] | 10,245 | qasper |
3d1fe2b6-7bc1-4827-9b04-0322fc6f38a2 | [{"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 model, LRCN1u"
] | 4,578 | qasper |
539cfad7-be0e-489d-a9b8-595f0a17ab33 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the state-of-the-art models?\n\nIntroduction\nAutomatic judgment prediction is to train a machine judge to determine whether a certain plea in a given civil case would be supported or rejected. In countries with civil law sys... | [
"SVM with lexical features in accordance with previous works BIBREF16 , BIBREF17 , BIBREF1 , BIBREF15 , BIBREF4, attention-based method BIBREF3 and other methods we deem important, some off-the-shelf RC models, including r-net BIBREF5 and AoA BIBREF6 , which are the leading models on SQuAD leaderboard"
] | 5,477 | qasper |
53b8e82a-3a8d-4ba1-8f4d-7fb99b01bcb0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their best results on the benchmark datasets?\n\nIntroduction\nIn the field of natural language processing (NLP), the most prevalent neural approach to obtaining sentence representations is to use recurrent neural networks (... | [
"accuracy of 87.0%"
] | 4,503 | qasper |
54396e21-c6e9-41f6-998a-f318d10df0ad | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the difference of the proposed model with a standard RNN encoder-decoder?\n\nIntroduction\nNatural Language Generation (NLG) plays a critical role in Spoken Dialogue Systems (SDS) with task is to convert a meaning representati... | [
"Introduce a \"Refinement Adjustment LSTM-based component\" to the decoder"
] | 5,828 | qasper |
5840c11b-dd68-4c1f-aafc-3a006dcef0fe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets did they use?\n\nIntroduction\nAccurate grapheme-to-phoneme conversion (g2p) is important for any application that depends on the sometimes inconsistent relationship between spoken and written language. Most prominently,... | [
"the Carnegie Mellon Pronouncing Dictionary BIBREF12, the multilingual pronunciation corpus collected by deri2016grapheme , ranscriptions extracted from Wiktionary"
] | 4,276 | qasper |
5b6c6d64-9160-431f-8a94-fcf007317986 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they compare lexicons?\n\nIntroduction\nSentiment analysis aims to uncover the emotion conveyed through information. In online social networks, sentiment analysis is mainly performed for political and marketing purposes, produc... | [
"1000 term groups based on the number of total annotations(200 term groups with 2 total annotations, 200 term groups with 3 total annotations, and so on up to term groups with 6 total annotations)"
] | 6,752 | qasper |
5c783763-bddf-4fc1-9840-3b4e42aba8c1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What do they mean by a person's industry?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friends a... | [
"the aggregate of enterprises in a particular field"
] | 5,300 | qasper |
5ee0a1cf-45df-435b-be35-2c6fda6e7a7d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the accuracy merits of the approach demonstrated?\n\nIntroduction\nEvent detection on microblogging platforms such as Twitter aims to detect events preemptively. A main task in event detection is detecting events of predetermi... | [
"By evaluating the performance of the approach using accuracy and AUC"
] | 6,676 | qasper |
68f6b10a-bcb9-4f22-a4f9-eb9f5290dbff | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the supervised scores of the words calculated?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by r... | [
"(+1 or -1), words of opposite polarities (e.g. “happy\" and “unhappy\") get far away from each other"
] | 5,006 | qasper |
7d65c6d7-91cc-47b2-a5e2-239258e74ae4 | [{"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... | [
"English, Chinese, Korean, we translated the English and Chinese datasets into more languages, with Google Translate"
] | 3,418 | qasper |
8924459c-e838-44ba-b381-4689907130be | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they detect spammers?\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 active users on the platform... | [
"Extract features from the LDA model and use them in a binary classification task"
] | 3,613 | qasper |
a3b22c1d-cd5d-42c7-a5c9-6d04e599d119 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators tagged each tweet?\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 the authors in any way, and the point... | [
"One experienced annotator tagged all tweets"
] | 7,104 | qasper |
c4fb5416-231f-4cf4-bf3a-816cbc3f4487 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines are presented?\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 has b... | [
"Logistic regression, LSTM, End-to-end memory networks, Deep projective reader"
] | 4,700 | qasper |
d96cdf50-d502-4bba-affe-4d0d8af09542 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How large is the collection of COVID-19 literature?\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 death... | [
"45,000 scholarly articles, including over 33,000 with full text"
] | 2,993 | qasper |
e334b2a5-e51e-404d-9461-67d23544d442 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they verify generalization ability?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/\nEntity linking (EL), mappi... | [
"By calculating Macro F1 metric at the document level."
] | 5,744 | qasper |
e39dd366-bedc-4692-8ba2-041cf0716ef1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the audio data gathered?\n\nINTRODUCTION\nThe idea of language identification is to classify a given audio signal into a particular class using a classification algorithm. Commonly language identification task was done using i... | [
"Through the All India Radio new channel where actors read news."
] | 3,267 | qasper |
f74ddbc6-83eb-4e22-8072-7a18520aefc1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the source of the news sentences?\n\nIntroduction\nNamed entity recognition is an important task of natural language processing, featuring in many popular text processing toolkits. This area of natural language processing has ... | [
"ilur.am"
] | 4,130 | qasper |
03149e14-5bbd-4e41-8e7d-ded72aedb9bb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What models are used for painting embedding and what for language style transfer?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the result... | [
"generating a poem from images we use an existing actor-critic architecture, various types of sequence to sequence models"
] | 2,144 | qasper |
0caa37c8-71c5-4696-b36e-be9d4236e71f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they perform multilingual training?\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... | [
"Multilingual training is performed by randomly alternating between languages for every new minibatch"
] | 3,048 | qasper |
2af4d7df-bb34-4dc5-b6bb-c00f7da89671 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which two news domains are country-independent?\n\nIntroduction and related work\nIn recent years there has been increasing interest on the issue of disinformation spreading on online social media. Global concern over false (or \"fake... | [
"mainstream and disinformation news"
] | 6,628 | qasper |
339a3431-bb76-466b-a1b1-4545211196f0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What details are given about the Twitter dataset?\n\nIntroduction\nSentiment analysis has recently been one of the hottest topics in natural language processing (NLP). It is used to identify and categorise opinions expressed by review... | [
"Those tweets are mostly much noisier and shorter compared to the reviews in the movie corpus. In total, there are 1,716 tweets. 973 of them are negative and 743 of them are positive."
] | 5,005 | qasper |
34f538a2-4db8-4af3-9d1a-302b57561b0b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What applicability of their approach is demonstrated by the authors?\n\nIntroduction\nNeural networks have been successfully used to describe images with text using sequence-to-sequence models BIBREF0. However, the results are simple ... | [
"Unanswerable"
] | 2,142 | qasper |
3ac49cb9-a6a7-4c6e-b5b0-edfd653e8e14 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset was used?\n\nIntroduction\nPropaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. In the Internet era, thanks to the mechanism of sharing in social networks, propaganda campaigns ... | [
"collected from 36 propagandist and 12 non-propagandist news outlets and then annotated by professional annotators"
] | 4,227 | qasper |
48fbbcde-37c2-40e1-b86c-6944b8ef6d8b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively examined from different pe... | [
"Yes"
] | 20,055 | qasper |
52967c31-294b-4d4b-9a80-5eb5e66bf321 | [{"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... | [
"When the perception of what we hear is influenced by what we see."
] | 4,431 | qasper |
54f2107f-f19c-4291-9c56-c75506dd2687 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a wizard of oz setup?\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 their infor... | [
"seeker interacts with a real conversational interface, intermediary (or the wizard) receives the seeker's message and performs different information seeking actions"
] | 2,271 | qasper |
677ae560-ff82-44d5-8c33-3f477c88fdba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What GAN models were used as baselines to compare against?\n\nIntroduction\nNatural text generation, as a key task in NLP, has been advanced substantially thanks to the flourish of neural models BIBREF0 , BIBREF1 . Typical frameworks ... | [
"SeqGAN, LeakGAN, MaliGAN, DialogGAN, DPGAN"
] | 5,224 | qasper |
6f6fd812-efff-4b2a-aa83-205337151fe7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are examples of these artifacts?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect and annotate data in multiple... | [
"hypothesis-only baseline performs better than chance due to cues on their lexical choice and sentence length, NLI models tend to predict entailment for sentence pairs with a high lexical overlap"
] | 5,513 | qasper |
77c91808-fc57-4aae-ad51-a6854556b413 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages for the English Wi... | [
"For Article-Entity placement, they consider two baselines: the first one using only salience-based features, and the second baseline checks if the entity appears in the title of the article. \n\nFor Article-Section Placement, they consider two baselines: the first picks the section with the highest lexical similar... | 10,236 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.