uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
ee4e7e35-4428-4926-8741-ab5d6079d1cb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metric do they use?\n\nIntroduction\nThis research addresses the problem of representing the semantics of text documents in multi-lingual comparable corpora. We present a new approach to this problem, based on neural e... | [
"ratio of correct `translations'"
] | 3,437 | qasper |
eefbdd6d-c610-4046-99ea-8f8c107add54 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"To what baseline models is proposed model compared?\n\nIntroduction\nMedical text mining is an exciting area and is becoming attractive to natural language processing (NLP) researchers. Clinical notes are an example of text in the med... | [
"support vector machine classifier (SVM), logistic regression classifier (LR), Naive Bayes classifier (NB), random forest (RF), CNN, LSTM , LSTM-soft, LSTM-self"
] | 4,065 | qasper |
f163297f-fe44-4a83-9239-934742d61c50 | [{"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 |
fd0c76fe-179f-4c58-8cb9-b9034a7a1334 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what ner models were evaluated?\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 been activ... | [
"Stanford NER, spaCy 2.0 , recurrent model with a CRF top layer"
] | 4,127 | qasper |
fe7616cd-0b00-4988-90ea-e6c23a8958fb | [{"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 |
07f4e8bc-71ed-485d-ac91-70b2c4cdf476 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different phenotypes are present in the dataset?\n\nIntroduction and Related Work\nWith the widespread adoption of electronic health records (EHRs), medical data are being generated and stored digitally in vast quantities BIB... | [
"15 clinical patient phenotypes"
] | 2,186 | qasper |
175ef93f-542a-4d44-bcb1-41dd36bb804b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What argument components do the ML methods aim to identify?\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 fr... | [
"claim, premise, backing, rebuttal, and refutation"
] | 20,057 | qasper |
20e0a2ad-4b33-43df-8e99-767b1e24ffe5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which two pairs of ERPs from the literature benefit from joint training?\n\nIntroduction\nThe cognitive processes involved in human language comprehension are complex and only partially identified. According to the dual-stream model o... | [
"Unanswerable"
] | 2,373 | qasper |
23a02dbe-3569-4c83-a1c6-3c661273a502 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which non-english language was the had the worst results?\n\nIntroduction\nWith the steady growth in the commercial websites and social media venues, the access to users' reviews have become easier. As the amount of data that can be m... | [
"Turkish"
] | 3,546 | qasper |
23fd29af-67da-4375-baa0-7a6a192e03a9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the position in the sequence part of the input?\n\nIntroduction\nOver the past few years, generating text from images and videos has gained a lot of attention in the Computer Vision and Natural Language Processing communities and s... | [
"Yes"
] | 1,776 | qasper |
240265b1-2eae-4b80-932e-809ebbe61ecf | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the different modules in Macaw?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy ... | [
"Co-Reference Resolution, Query Generation, Retrieval Model, Result Generation"
] | 2,272 | qasper |
2691dc3a-e6ca-4358-93c7-6261b135e64f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the authors evidence the claim that many engineers find it a big overhead to choose from multiple frameworks, models and optimization techniques?\n\nIntroduction\nDeep Neural Networks (DNN) have been widely employed in industry... | [
"Unanswerable"
] | 2,372 | qasper |
26ddd892-9928-4af9-85bc-fee2251ddaae | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method's improvements of F1 for NER task for English and Chinese datasets?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives con... | [
"English datasets including CoNLL2003 and OntoNotes5.0, our proposed method outperforms BERT-MRCBIBREF38 by +0.29 and +0.96 respectively, Chinese datasets, achieving F1 improvements by +0.97 and +2.36 on MSRA and OntoNotes4.0, respectively"
] | 5,647 | qasper |
395dcb96-4293-46cd-a613-16fc457fe03b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which methods are considered to find examples of biases and unwarranted inferences??\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to tr... | [
"Looking for adjectives marking the noun \"baby\" and also looking for most-common adjectives related to certain nouns using POS-tagging"
] | 2,935 | qasper |
3c31f5da-9952-4756-910d-f135c33a4269 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On which tasks do they test their conflict method?\n\nIntroduction\nModelling the relationship between sequences is extremely significant in most retrieval or classification problems involving two sequences. Traditionally, in Siamese ... | [
"Task 1: Quora Duplicate Question Pair Detection, Task 2: Ranking questions"
] | 3,182 | qasper |
49319bbd-6683-48b9-8234-8bc0c70183c8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they only experiment with one language pair?\n\nIntroduction\nReordering in machine translation (MT) is a crucial process to get the correct translation output word order given an input source sentence, as word order reflects mean... | [
"Yes"
] | 6,022 | qasper |
4a94068a-77fe-434a-8d01-b95625f2a359 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What labels do they create on their dataset?\n\nProblem Statement\nSpoken conversations still remain the most natural and effortless means of human communication. Thus a lot of valuable information is conveyed and exchanged in such an... | [
"(1) the time the patient has been experiencing the symptom, (2) activities that trigger the symptom (to occur or worsen), (3) the extent of seriousness, (4) the frequency occurrence of the symptom, and (5) the location of symptom, No Answer"
] | 4,628 | qasper |
4dd077c1-f3f7-495b-aed3-ec8f2bc3c7d0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\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 in Twi... | [
"LastStateRNN, AvgRNN, AttentionRNN "
] | 3,864 | qasper |
54ed54e3-7ab5-4eeb-9337-065ddab1b6fe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On which tasks do they test their conflict method?\n\nIntroduction\nModelling the relationship between sequences is extremely significant in most retrieval or classification problems involving two sequences. Traditionally, in Siamese ... | [
"Quora Duplicate Question Pair Detection, Ranking questions in Bing's People Also Ask"
] | 3,182 | qasper |
5a93a0a6-d86b-4fda-8693-0f799b62debe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which matrix factorization methods do they use?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, and many ot... | [
"The LexVec BIBREF7"
] | 3,205 | qasper |
5e1c4fdb-bd74-41c3-8955-d0efdb512445 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the state of the art system mentioned?\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... | [
"Two knowledge-based systems,\ntwo traditional word expert supervised systems, six recent neural-based systems, and one BERT feature-based system."
] | 3,004 | qasper |
6a15432d-e215-4135-9917-bed66faf5ea3 | [{"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 |
6a688676-68d0-4ac4-9313-896273ce9543 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which real-world datasets are used?\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 BIBREF0, suc... | [
"Tweets related to CyberAttack and tweets related to PoliticianDeath"
] | 6,673 | qasper |
789847fa-6652-4982-b1a3-6baec1097590 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How better is performance compared to previous state-of-the-art models?\n\nIntroduction\nChinese word segmentation (CWS) is a task for Chinese natural language process to delimit word boundary. CWS is a basic and essential task for Ch... | [
"MSR: 97.7 compared to 97.5 of baseline\nAS: 95.7 compared to 95.6 of baseline"
] | 5,087 | qasper |
83e664cc-debf-41a8-8863-04262563f610 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What accuracy does the proposed system achieve?\n\nIntroduction\nThere has been significant progress on Named Entity Recognition (NER) in recent years using models based on machine learning algorithms BIBREF0 , BIBREF1 , BIBREF2 . As ... | [
"F1 scores of 85.99 on the DL-PS data, 75.15 on the EC-MT data and 71.53 on the EC-UQ data "
] | 8,638 | qasper |
8a79e5c1-1861-4c26-8e8c-80c89a964180 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much time takes its training?\n\nIntroduction\nIn this publication, we present Sentence-BERT (SBERT), a modification of the BERT network using siamese and triplet networks that is able to derive semantically meaningful sentence em... | [
"20 minutes"
] | 5,615 | qasper |
97b98c0f-89d2-4302-a38d-bc1c3be5638c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Was the approach used in this work to detect fake news fully supervised?\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... | [
"Yes"
] | 2,889 | qasper |
99b67e57-5963-41e8-bd06-28537b1c69d6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English?\n\nIntroduction\nDeep Neural Networks (DNN) have been widely employed in industry for solving various Natural Language Processing (NLP) tasks, such as text classification, sequence labeling, que... | [
"Unanswerable"
] | 2,354 | qasper |
9d47abe7-28fa-4c3a-bee8-33e0f38c7e96 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"by how much did nus outperform abus?\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 findin... | [
"Average success rate is higher by 2.6 percent points."
] | 6,344 | qasper |
ad581ab3-c3fa-4d81-802e-384375159a45 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what way does LiLi imitate how humans acquire knowledge and perform inference during an interactive conversation?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural languag... | [
"newly acquired facts are retained in the KB and used in inference for future queries, and that the accumulated knowledge in addition to the updated KB including past inference performances are leveraged to guide future interaction and learning"
] | 8,590 | qasper |
b82d9dd3-cbd9-45a0-abc4-fa50277774ca | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the score of the proposed model?\n\nIntroduction\nQuestion answering (QA) has drawn a lot of attention in the past few years. QA tasks on images BIBREF0 have been widely studied, but most focused on understanding text documen... | [
"EM Score of 51.10"
] | 3,115 | qasper |
bd1d7c39-759e-47b9-9d4d-103f8236a747 | [{"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 , two alternative annotations of the CoNLL 2014 Shared Task dataset"
] | 2,711 | qasper |
c07058c5-8a00-48fc-a3f8-df2f06391a7f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the two new strategies?\n\nIntroduction and Background\nMany reinforcement learning algorithms are designed for relatively small discrete or continuous action spaces and so have trouble scaling. Text-adventure games—or intera... | [
"KG-A2C-chained, KG-A2C-Explore"
] | 3,183 | qasper |
cb040e34-d716-46b7-bdbd-ef86c5d63155 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is NER?\n\nIntroduction\nThe explosion of available scientific articles in the Biomedical domain has led to the rise of Biomedical Information Extraction (BioIE). BioIE systems aim to extract information from a wide spectrum of a... | [
"Named Entity Recognition, including entities such as proteins, genes, diseases, treatments, drugs, etc. in the biomedical domain"
] | 3,928 | qasper |
cb12817b-9b97-413e-90e8-68a3af0b7574 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which is more useful, visual or textual features?\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, inclu... | [
"It depends on the dataset. Experimental results over two datasets reveal that textual and visual features are complementary. "
] | 5,709 | qasper |
cee1a39f-27d7-4c41-9985-cbfcc4174592 | [{"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 QUESTION ANSWERING"
] | 9,206 | qasper |
d08bbb7f-4b64-4392-8bf1-f5e1221fa353 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of model do they use?\n\nIntroduction\nThe task of document quality assessment is to automatically assess a document according to some predefined inventory of quality labels. This can take many forms, including essay scoring... | [
"visual model is based on fine-tuning an Inception V3 model BIBREF1 over visual renderings of documents, while our textual model is based on a hierarchical biLSTM. We further combine the two into a joint model. , neural network models"
] | 5,707 | qasper |
e773c053-37de-49ba-9ab1-ccb506bcce72 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation metrics did they use?\n\nIntroduction\nText simplification aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning, which can help children, non-native speakers, and p... | [
"BLEU , FKGL , SARI "
] | 3,185 | qasper |
ef742f03-c28d-41fa-b62f-2c6cfd0ee701 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline?\n\nIntroduction\nAutomatic classification of sentiment has mainly focused on categorizing tweets in either two (binary sentiment analysis) or three (ternary sentiment analysis) categories BIBREF0 . In this work ... | [
"SVM INLINEFORM0, SVM INLINEFORM1, LR INLINEFORM2, MaxEnt"
] | 3,585 | qasper |
efb610a9-10fc-4cb9-b4a8-62adfd7d4f5f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what surface-level features are 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 typi... | [
"affixes, leading and trailing characters in words and stems, and the presence of words in large gazetteers of named entities"
] | 7,072 | qasper |
f315bee2-ccd7-46bb-8940-bf64297ccd9f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the best model?\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 othersBIBREF0. The... | [
"BiLSTM+CNN(grapheme-level) and BiLSTM+CNN(G)+POS "
] | 4,285 | qasper |
087a9877-dc2d-4a07-9b6b-b5954f6f3bad | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were their results on the new dataset?\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 ... | [
"average recipe-level coherence scores of 1.78-1.82, human evaluators preferred personalized model outputs to baseline 63% of the time"
] | 3,951 | qasper |
13706856-6a49-4c0a-bc0c-51376dc3933e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what data simulation techniques were introduced?\n\nIntroduction \nThe new generation of Neural Machine Translation (NMT) systems is known to be extremely data hungry BIBREF0 . Yet, most existing NMT training pipelines fail to fully t... | [
"copy, copy-marked, copy-dummies"
] | 5,627 | qasper |
19e98dc5-75fa-4b6a-9185-3501a1d5dac9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many tweets are in the dataset?\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 of... | [
"10,000 Arabic tweet dataset "
] | 7,104 | qasper |
19fcaa60-539f-46c9-8244-8b32d3d6f3b9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines do they compare to?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is the anonymity for th... | [
"LR + Bag-of-words, Tweet2vec, LR + All Features (tweet-level), LR + All Features (chunk-level), FacTweet (tweet-level), Top-$k$ replies, likes, or re-tweets"
] | 2,883 | qasper |
286ddee5-2f73-4afa-b683-e2da9e6be98b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics do they use?\n\nIntroduction\nQuestion Generation (QG) is the task of automatically creating questions from a range of inputs, such as natural language text BIBREF0, knowledge base BIBREF1 and image BIBREF2. QG is an incr... | [
"BLEU-1 (B1), BLEU-2 (B2), BLEU-3 (B3), BLEU-4 (B4) BIBREF17, METEOR (MET) BIBREF18 and ROUGE-L (R-L) BIBREF19"
] | 5,603 | qasper |
287b35fc-3f39-40cb-825d-83d915410251 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they determine the exact section to use the input article?\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 wi... | [
"They use a multi-class classifier to determine the section it should be cited"
] | 10,243 | qasper |
28e3e88c-24fa-4862-932c-ad9aba94cd08 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Ngrams of which length are aligned using PARENT?\n\nIntroduction\nThe task of generating natural language descriptions of structured data (such as tables) BIBREF2 , BIBREF3 , BIBREF4 has seen a growth in interest with the rise of sequ... | [
"Answer with content missing: (Parent subsections) combine precisions for n-gram orders 1-4"
] | 5,085 | qasper |
29788a48-5ca0-4435-9766-320db42e61fb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used to train the model?\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... | [
"2,50,000 tweets, Stock opening and closing prices of Microsoft from August 31st, 2015 to August 25th, 2016"
] | 3,163 | qasper |
2fa93eef-a929-4471-9c69-cf023bfeef06 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does the IPA label data after interacting with users?\n\nIntroduction\nRobotic Process Automation (RPA) is a type of software bots that simulates hand-operated human activities like entering data into a system, registering into ac... | [
"Plain dialogues with unique dialogue indexes, Plain Information Dictionary information (e.g., extracted entities) collected for the whole dialogue, Pairs of questions (i.e., user requests) and responses (i.e., bot responses), Triples in the form of (User Request, Next Action, Response)"
] | 8,436 | qasper |
39519ec8-1771-4f1e-8996-461eb34e2d59 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the difficulties in modelling the ironic pattern?\n\nIntroduction\nThe irony is a kind of figurative language, which is widely used on social media BIBREF0 . The irony is defined as a clash between the intended meaning of a s... | [
"obscure and hard to understand, lack of previous work and baselines on irony generation"
] | 6,082 | qasper |
3da7d26b-6197-49a7-b060-db3551da188f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they select instances to their hold-out test set?\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 exchange... | [
"held out from the simulated data"
] | 4,631 | qasper |
3f2bd7ff-d19d-4d73-8715-4a71c07b5aff | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate their learned representations on downstream tasks?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic representation of ... | [
"No"
] | 2,510 | qasper |
4355dd68-55c2-4463-921c-362068624a3c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the 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 othersBIB... | [
"Dataset contains 3606 total sentences and 79087 total entities."
] | 4,287 | qasper |
4a676699-53b7-42b1-aeb1-649ad740aa89 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baselines?\n\nIntroduction\nCLIR systems retrieve documents written in a language that is different from search query language BIBREF0 . The primary objective of CLIR is to translate or project a query into the language o... | [
"baseline transformer BIBREF8"
] | 2,858 | qasper |
4cf5f94a-3e81-4d06-a729-94bfb67e6103 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are sentences selected from the summary graph?\n\nIntroduction\nSummarization of large texts is still an open problem in language processing. People nowadays have lesser time and patience to go through large pieces of text which m... | [
" Two methods: first is to simply pick initial few sentences, second is to capture the relation between the two most important entities (select the first sentence which contains both these entities)."
] | 5,732 | qasper |
504c6f60-ebf1-4682-b8ca-9105d39e8996 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much is classification performance improved in experiments for low data regime and class-imbalance problems?\n\nIntroduction\nThe performance of machines often crucially depend on the amount and quality of the data used for traini... | [
"Low data: SST-5, TREC, IMDB around 1-2 accuracy points better than baseline\nImbalanced labels: the improvement over the base model increases as the data gets more imbalanced, ranging from around 6 accuracy points on 100:1000 to over 20 accuracy points on 20:1000"
] | 6,948 | qasper |
5db4e59e-fed3-496f-927c-9820ec66070a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What word embeddings do they test?\n\nIntroduction\nEquations are an important part of scientific articles, but many existing machine learning methods do not easily handle them. They are challenging to work with because each is unique... | [
"Bernoulli embeddings (b-emb) BIBREF1 , continuous bag-of-words (CBOW) BIBREF5 , Distributed Memory version of Paragraph Vector (PV-DM) BIBREF11 and the Global Vectors (GloVe) BIBREF6 model"
] | 3,789 | qasper |
6d050a85-a4c4-4d21-9feb-a467d22902c7 | [{"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 model, Lead-1-AMR, BIBREF0 "
] | 5,731 | qasper |
7483c4c3-e5a6-4e30-b9ca-3f42cc386136 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper provide any case studies to illustrate how one can use Macaw for CIS research?\n\nIntroduction\nThe rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the wa... | [
"No"
] | 2,282 | qasper |
864275ad-c48f-4d88-a1ba-73cb4a6b645f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what datasets did they use?\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 questions based on e... | [
"Dataset of total 3500 questions from the Internet and other sources such as books of general knowledge questions, history, etc."
] | 2,874 | qasper |
977f9db1-11a0-4274-babd-bfcfb07c8eb2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which classifiers are evaluated?\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 platform... | [
"SVM, MLP, FastText, CNN, BERT, DialogFlow, Rasa NLU"
] | 3,153 | qasper |
989609f4-3b33-4bc0-bec9-6f619deab80b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the human judgements assembled?\n\nIntroduction\nThe use of RNNs in the field of Statistical Machine Translation (SMT) has revolutionised the approaches to automated translation. As opposed to traditional shallow SMT models, ... | [
"50 human annotators ranked a random sample of 100 translations by Adequacy, Fluency and overall ranking on a 5-point scale."
] | 6,989 | qasper |
996caecd-1d34-4ede-b6ed-36839113a05e | [{"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,... | [
"multilingual pronunciation corpus collected by deri2016grapheme"
] | 4,276 | qasper |
aa0566ba-8795-485a-80a3-5c4f5de6e2c1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does Gaussian-masked directional multi-head attention works?\n\nIntroduction\nChinese word segmentation (CWS) is a task for Chinese natural language process to delimit word boundary. CWS is a basic and essential task for Chinese w... | [
"Gaussian-masked directional attention can be described as a function to map queries and key-value pairs to the representation of input, Gaussian-masked directional attention expects to pay attention to the adjacent characters of each positions and cast the localness relationship between characters as a fix Gaussia... | 5,085 | qasper |
b15d6087-3bbe-44cf-a436-d33be91bd304 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On what datasets are experiments performed?\n\nIntroduction\nQuestion Generation (QG) is the task of automatically creating questions from a range of inputs, such as natural language text BIBREF0, knowledge base BIBREF1 and image BIBR... | [
"SQuAD"
] | 5,604 | qasper |
b8110724-0280-4e62-b637-e4e218961f5a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is this method improvement over the best performing state-of-the-art?\n\nIntroduction\nHeadline generation is the process of creating a headline-style sentence given an input article. The research community has been regarding the... | [
"absolute improvement of 18.2% over the Pointer-Gen baseline"
] | 6,352 | qasper |
b94e16e1-ca83-4691-bf75-6508d8680bdc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the state of the art described in the paper?\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 hig... | [
"ELIZA, PARRY, A.L.I.C.E., Cleverbot"
] | 17,795 | qasper |
d8c94ef4-6c46-4974-97cb-d4119579032f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"For which languages do they build word embeddings for?\n\nIntroduction\nLow dimensional word representations (embeddings) have become a key component in modern NLP systems for language modeling, parsing, sentiment classification, and ... | [
"Unanswerable"
] | 3,206 | qasper |
e4be95c2-0013-4d41-aa99-2c348f21173a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which neural architecture do they use as a base for their attention conflict mechanisms?\n\nIntroduction\nModelling the relationship between sequences is extremely significant in most retrieval or classification problems involving two... | [
"two stacked GRU layers, attention for one model while for the another one it consists of attention and conflict combined, fully-connected layers"
] | 3,187 | qasper |
e8cf0533-cd5c-478a-85b2-3b4a9f479383 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for evaluation?\n\nIntroduction\nRendering natural language descriptions from structured data is required in a wide variety of commercial applications such as generating descriptions of products, hotels, furnitur... | [
"BLEU-4, NIST-4, ROUGE-4"
] | 5,867 | qasper |
eac4416a-f901-4ad0-8122-33c4b7e45cea | [{"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... | [
"Data already contain errors"
] | 6,342 | qasper |
00bf862c-280d-4320-9e71-6400fbd1b264 | [{"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... | [
"semantics-altering grammatical modifiers"
] | 6,569 | qasper |
021c0747-f86d-4822-80f9-bdd25764910f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were their performance results?\n\nIntroduction\nMedical search engines are an essential component for many online medical applications, such as online diagnosis systems and medical document databases. A typical online diagnosis ... | [
"hybrid NER model achieved a F1 score of $0.995$ on synthesized queries and $0.948$ on clinical notes"
] | 4,884 | qasper |
0b1312bd-190e-4ccd-826c-6d8c38cb79d9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset statistics are provided?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people ... | [
"Distribution of category labels, number of answerable-not answerable questions, number of text-based and script-based questions, average text, question, and answer length, number of questions per text"
] | 5,793 | qasper |
134622c3-f0f8-40f6-924e-d976c4daff5d | [{"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... | [
"It does not use a seed list to gather tweets so the dataset does not skew to specific topics, dialect, targets."
] | 7,112 | qasper |
19341154-53ce-45c0-b56a-63c7f4e5a79c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much data is needed to train the task-specific encoder?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the... | [
"57,505 sentences"
] | 5,763 | qasper |
2487d1fc-3187-451b-832f-6e98c0fcebb4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used for evaluation?\n\nIntroduction\nPre-trained models BIBREF0, BIBREF1 have received much of attention recently thanks to their impressive results in many down stream NLP tasks. Additionally, multilingual pre-train... | [
"translation probabilities, Labeled Attachment Scores (LAS)"
] | 5,300 | qasper |
4931ca57-31b8-4224-869b-e79cf53613f0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Have they made any attempt to correct MRC gold standards according to their findings? \n\nIntroduction\nThere is a recent spark of interest in the task of Question Answering (QA) over unstructured textual data, also referred to as Mac... | [
"Yes"
] | 6,569 | qasper |
4f5b54ce-af5c-45d4-8477-904bd86e3bf1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the corpus contain only English documents?\n\nIntroduction\nMulti-document summarization (MDS), the transformation of a set of documents into a short text containing their most important aspects, is a long-studied problem in NLP.... | [
"Yes"
] | 5,674 | qasper |
563044df-c560-4b79-aac9-06fdf95fadee | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the Chinese data?\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 w... | [
"32,595"
] | 5,898 | qasper |
60f0731c-1752-4093-9328-1d9d25a60f16 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they model semantics \n\nKeywords:\ncomputational sociolinguistics, dehumanization, lexical variation, language change, media, New York Times, LGBTQ\nWarning: this paper contains material that some may find offensive or upsetting.\... | [
"Yes"
] | 17,771 | qasper |
6b8f326f-859d-43b4-88af-4ab10188d08a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much training data from the non-English language is used by the system?\n\nIntroduction\nPre-trained models BIBREF0, BIBREF1 have received much of attention recently thanks to their impressive results in many down stream NLP tasks... | [
"No data. Pretrained model is used."
] | 5,309 | qasper |
6bf6c4da-e6e2-493d-8363-9f7b242a682c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the datasets annotated?\n\nIntroduction\nThe lack of annotated training and evaluation data for many tasks and domains hinders the development of computational models for the majority of the world's languages BIBREF0, BIBREF1... | [
"1. Each annotator must assign an integer score between 0 and 6 (inclusive) indicating how semantically similar the two words in a given pair are. A score of 6 indicates very high similarity (i.e., perfect synonymy), while zero indicates no similarity., 2. Each annotator must score the entire set of 1,888 pairs in ... | 21,901 | qasper |
785c26e4-7aa9-410e-a687-7ff531b3041a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they collect their own datasets?\n\nWinograd Schemas\nA Winograd schema (Levesque, Davis, and Morgenstern 2012) is a pair of sentences, or of short texts, called the elements of the schema, that satisfy the following constraints:\... | [
"No"
] | 3,340 | qasper |
9d61cbde-95c7-4797-a29e-93c005bf5691 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the authors examine whether a model is robust to noise or not?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions. Since the answer... | [
"By evaluating their model on adversarial sets containing misleading sentences"
] | 5,694 | qasper |
9eca1ef7-f65f-40fd-bb6a-0914b8e32d67 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what evaluation metrics were used?\n\nIntroduction\nAccurate grapheme-to-phoneme conversion (g2p) is important for any application that depends on the sometimes inconsistent relationship between spoken and written language. Most promi... | [
"Phoneme Error Rate (PER), Word Error Rate (WER), Word Error Rate 100 (WER 100)"
] | 4,276 | qasper |
b047a2b2-edfb-481c-8174-5b78aa076570 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\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 ... | [
"Unanswerable"
] | 5,496 | qasper |
b53b505f-3faf-4877-ad55-cf6fa1a0ad95 | [{"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 for question-relation matching, build both relation-level and word-level relation representations, use deep bidirectional LSTMs (BiLSTMs) to learn different levels of question representations, residual learning method for sequence matching, a simple KBQA implementation ... | 6,738 | qasper |
c7c4d050-991c-40d0-86cf-fcf1a466b9cd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"After how many hops does accuracy decrease?\n\nIntroduction\nAutomatically answering questions, especially in the open-domain setting (i.e., where minimal or no contextual knowledge is explicitly provided), requires bringing to bear c... | [
"1-hop links to 2-hops"
] | 9,200 | qasper |
c85dcce3-2b4d-4c04-930c-e839a39e9641 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the weaknesses found by non-expert annotators of current state-of-the-art NLI models?\n\nIntroduction\nProgress in AI has been driven by, among other things, the development of challenging large-scale benchmarks like ImageNet... | [
"state-of-the-art models learn to exploit spurious statistical patterns in datasets, human annotators—be they seasoned NLP researchers or non-experts—might easily be able to construct examples that expose model brittleness"
] | 6,716 | qasper |
ccb8b0b0-c120-44ab-a51b-08d6e9d4b931 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which models are used to solve NER for Nepali?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into specific categories like \"PERSON\", \"LOCATION\", \"ORGANIZATION\"... | [
"BiLSTM, BiLSTM+CNN, BiLSTM+CRF, BiLSTM+CNN+CRF, CNN, Stanford CRF"
] | 4,291 | qasper |
db5c32c5-4f0a-4f1d-9350-0df973a97444 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the language pairs explored in this paper?\n\nIntroduction\nNeural machine translation (NMT) emerged in the last few years as a very successful paradigm BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . While NMT is generally more flue... | [
"De-En, Ja-En, Ro-En"
] | 2,303 | qasper |
e433c504-9fa1-4068-b41c-1d8dc0875563 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other examples of morphologically-rich languages do the authors give?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems. The... | [
"Russian"
] | 4,026 | qasper |
e521cdfa-31b4-4d22-99ba-9a626e19f4d8 | [{"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... | [
"diacritized corpus that was used to train the RDI BIBREF7 diacritizer and the Farasa diacritizer BIBREF31, WikiNews test set BIBREF31, large collection of fully diacritized classical texts (2.7M tokens) from a book publisher"
] | 7,070 | qasper |
f077b0ee-9b89-4cb2-ac2c-dfe857dca2d4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what dataset was 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 500 million tweets ar... | [
"WASSA-2017 Shared Task on Emotion Intensity"
] | 2,363 | qasper |
f52eaf0e-8575-433c-a241-f5f42434ed57 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks are used for evaluation?\n\nIntroduction\nThe Transformer architecture BIBREF0 for deep neural networks has quickly risen to prominence in NLP through its efficiency and performance, leading to improvements in the state of ... | [
"four machine translation tasks: German -> English, Japanese -> English, Romanian -> English, English -> German"
] | 7,818 | qasper |
fa1b8e38-2b81-47b8-b20d-e200511e34e7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What word-based and dictionary-based feature are used?\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... | [
"generate word embeddings specific to a domain, TDK (Türk Dil Kurumu - “Turkish Language Institution”) dictionary to obtain word polarities"
] | 5,006 | qasper |
fdd39f5b-e628-435c-a9df-6d8384f6b1e4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the invertibility condition?\n\nIntroduction\nData annotation is a major bottleneck for the application of supervised learning approaches to many problems. As a result, unsupervised methods that learn directly from unlabeled d... | [
"we constrain our neural projector with two requirements: (1) INLINEFORM0 and (2) INLINEFORM1 exists"
] | 5,842 | qasper |
0b632f97-56e9-43b0-a4c0-c89293421141 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nState-of-the-art automatic speech recognition (ASR) systems BIBREF0 have large model capacities and require significant quantities of training data to generalize. Labeling thousands of hours... | [
"trained on 190 hours ( INLINEFORM1 100K instances) of transcribed speech data, selects a subset of a 1,700-hour ( INLINEFORM2 1.1M instances) unlabeled dataset"
] | 2,231 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.