uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
1ebccc39-09f6-432c-a73c-592b61935f3d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how did the authors translate the reviews to other languages?\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 ... | [
"Using Google translation API."
] | 3,545 | qasper |
287da0ff-a59a-4d57-a61c-68fc87d8f2a2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What discourse relations does it work best/worst for?\n\nIntroduction\nPDTB-style discourse relations, mostly defined between two adjacent text spans (i.e., discourse units, either clauses or sentences), specify how two discourse unit... | [
"Best: Expansion (Exp). Worst: Comparison (Comp)."
] | 5,574 | qasper |
2a98922a-dc49-496a-bd96-0788a8272c43 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors hypothesize that humans' robustness to noise is due to their general knowledge?\n\nIntroduction\nMachine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant qu... | [
"Yes"
] | 5,698 | qasper |
2b02dadd-b75a-4b1b-a4de-c82fab348b19 | [{"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 |
315e3da6-4fae-4bf9-9e4d-1540f49cbe0a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are used?\n\nIntroduction\nCancer is one of the leading causes of death in the world, with over 80,000 deaths registered in Canada in 2017 (Canadian Cancer Statistics 2017). A computer-aided system for cancer diagnosis u... | [
"Unanswerable"
] | 2,754 | qasper |
3b976fa5-bc7a-4f86-b856-8fb12a13f2b2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the scores of their system?\n\nIntroduction\nUnderstanding the emotions expressed in a text or message is of high relevance nowadays. Companies are interested in this to get an understanding of the sentiment of their current... | [
"column Ens Test in Table TABREF19"
] | 3,100 | qasper |
54530678-1480-4f14-bfbc-817b3b2dcbe1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluations methods do they take?\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to train and evaluate neural network models that ge... | [
"Unanswerable"
] | 2,926 | qasper |
574fa575-8b75-4dd7-b445-1c358d06acba | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments are used to demonstrate the benefits of this approach?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semant... | [
"On each dataset, we compare four approaches based on sefe with two efe BIBREF10 baselines. All are fit using sgd BIBREF34 . In particular, we compare the following methods:"
] | 4,298 | qasper |
5f370746-5df1-48a2-b7e9-acd6ee9a0559 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where does the ancient Chinese dataset come from?\n\nIntroduction\nAncient Chinese is the writing language in ancient China. It is a treasure of Chinese culture which brings together the wisdom and ideas of the Chinese nation and chro... | [
"Ancient Chinese history records in several dynasties and articles written by celebrities during 1000BC-200BC collected from the internet "
] | 5,114 | qasper |
618eceba-3544-4df5-84ad-ccffabd17ae7 | [{"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... | [
"GRU-based encoder, interaction block, and classifier consisting of stacked fully-connected layers."
] | 3,187 | qasper |
61dc5751-cded-46ed-a1d2-7e7bf173b5c3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What transfer learning tasks are evaluated?\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 s... | [
"Semantic Textual Similarity, sentiment prediction, subjectivity prediction, phrase level opinion polarity classification, Stanford Sentiment Treebank, fine grained question-type classification."
] | 5,615 | qasper |
64d770ff-8cd2-48f9-8cf4-4cb8e28f81ab | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are prominent topics idenified in Dabiq and Rumiyah?\n\nIntroduction\nSince its rise in 2013, the Islamic State of Iraq and Syria (ISIS) has utilized the Internet to spread its ideology, radicalize individuals, and recruit them to... | [
"LDA, non-negative matrix factorization (NMF)"
] | 4,677 | qasper |
6977c5a6-f9e2-4df4-ba31-d6423a7b9e0a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they evaluate on English only datasets?\n\nIntroduction\nWord embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , BIBREF6 are unsupervised learning methods for capturing latent semantic structure in language. Wor... | [
"Unanswerable"
] | 4,294 | qasper |
7f1821ae-98dd-45d2-b830-498fe762ccb1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic representation of tweets can benefit a plethora of applicat... | [
"Unanswerable"
] | 2,506 | qasper |
8836d608-cc39-49c6-9562-39c158cb9964 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What current state of the art method was used for comparison?\n\nIntroduction\nA hashtag is a keyphrase represented as a sequence of alphanumeric characters plus underscore, preceded by the # symbol. Hashtags play a central role in on... | [
" BIBREF14, BIBREF15 "
] | 5,418 | qasper |
8954e2aa-b881-4ffd-82f6-82c7066cadc8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which other hyperparameters, other than number of clusters are typically evaluated in this type of research?\n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in p... | [
"selection of word vectors"
] | 3,571 | qasper |
8e1d05e7-f366-4c76-b8e5-7bfa8d526e9c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the attention module pretrained on?\n\nIntroduction\nSpeech-to-Text translation (ST) is essential for a wide range of scenarios: for example in emergency calls, where agents have to respond emergent requests in a foreign langu... | [
"the model is pre-trained on CTC-based ASR task and MT task in the pre-training stage."
] | 7,493 | qasper |
9df9903f-71d9-437c-b030-9b146a9617a5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset do they use for analysis?\n\nIntroduction\nIn June 2015, the operators of the online discussion site Reddit banned several communities under new anti-harassment rules. BIBREF0 used this opportunity to combine rich online ... | [
"Unanswerable"
] | 10,569 | qasper |
a4ea9e2c-229d-47d3-bf40-7c14ad7cef6c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what language pairs are explored?\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 take advantage o... | [
"English-German, English-French"
] | 5,626 | qasper |
abd213af-63a0-4256-bd89-c03a3f98a8b8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nTwitter is a widely used microblogging platform, where users post and interact with messages, “tweets”. Understanding the semantic representation of tweets can benefit a plethora of applicat... | [
" Paraphrase Database (PPDB) , book corpus"
] | 2,506 | qasper |
b7afe05e-d86e-4254-82c6-e46d5bb5324c | [{"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.... | [
"Unanswerable"
] | 5,674 | qasper |
b813850b-e3c0-4786-80f3-bf604a4595e4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which types of named entities do they recognize?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opinions and preferences of groups and individuals. These insights are... | [
"PER, LOC, ORG, MISC"
] | 5,441 | qasper |
bdc42498-2617-4cf1-9047-bb40ec76e46d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline models are used?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BIBREF0. This is largely due to inabilities of dia... | [
"the Poly-encoder from BIBREF7 humeau2019real, Feed Yourself BIBREF13 is an open-domain dialogue agent with a self-feeding model, Kvmemnn BIBREF14 is a key-value memory network with a knowledge base that uses a key-value retrieval mechanism to train over multiple domains simultaneously, We compare against four dial... | 7,235 | qasper |
c24d1ca6-e3aa-4373-810a-2d9a3e65babe | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the experts comparable to real-world users?\n\nIntroduction\nPrivacy policies are the documents which disclose the ways in which a company gathers, uses, shares and manages a user's data. As legal documents, they function using th... | [
"No"
] | 5,280 | qasper |
c6f73744-79ba-4952-aad1-a0479ce566e2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the domain of the corpus?\n\nIntroduction\nTypical speech-to-text translation systems pipeline automatic speech recognition (ASR) and machine translation (MT) BIBREF0 . But high-quality ASR requires hundreds of hours of transc... | [
"Unanswerable"
] | 2,066 | qasper |
c78e4699-e9ab-426d-bb87-74f54fd43595 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was their system's performance?\n\nIntroduction\nThe apparent rise in political incivility has attracted substantial attention from scholars in recent years. These studies have largely focused on the extent to which politicians a... | [
"accuracy and F1-score of 89.6% and 89.2%, respectively"
] | 4,410 | qasper |
c9b04467-0e0b-4d1f-bba9-e328a87abb9e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the model evaluated on NLG datasets or dialog datasets?\n\nIntroduction\nNatural Language Generation (NLG) plays a critical role in Spoken Dialogue Systems (SDS) with task is to convert a meaning representation produced by the Di... | [
"NLG datasets"
] | 5,823 | qasper |
e0bc259b-f74d-4f39-b026-0a3feb700e90 | [{"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 |
f32f27d0-884b-47c4-aa4a-9c0d97c0861b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What error types is their model more reliable for?\n\nIntroduction\nSequence-to-sequence (seq2seq) transformations have recently proven to be a successful framework for several natural language processing tasks, like: machine translat... | [
"grammatical, spelling and word order errors"
] | 6,337 | qasper |
0800c792-97c7-42a0-af9e-7936c692d1aa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is non-standard pronunciation identified?\n\nIntroduction\nRecent years have seen unprecedented progress for Natural Language Processing (NLP) on almost every NLP subtask. Even though low-resource settings have also been explored,... | [
"Unanswerable"
] | 4,176 | qasper |
08a99d1f-fe97-4cba-9b77-f20f3b2a62f5 | [{"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... | [
"pays attentions to adjacent characters and casts a localness relationship between the characters as a fixed Gaussian weight assuming the weight relies on the distance between characters"
] | 5,085 | qasper |
1b19c829-ae7b-4a89-8c7a-cee64eceea07 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What pooling function is used?\n\nIntroduction\nRecurrent neural networks (RNNs), including gated variants such as the long short-term memory (LSTM) BIBREF0 have become the standard model architecture for deep learning approaches to s... | [
"dynamic average pooling"
] | 4,696 | qasper |
1bf1c864-fd89-4585-8ad2-177acdb00d2b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the dataset?\n\nIntroduction\nThe Flickr30K dataset BIBREF0 is a collection of over 30,000 images with 5 crowdsourced descriptions each. It is commonly used to train and evaluate neural network models that generate... | [
"collection of over 30,000 images with 5 crowdsourced descriptions each"
] | 2,927 | qasper |
1c9eba19-8517-48fe-ada2-9fabbf00f10d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is it possible to convert a cloze-style questions to a naturally-looking questions?\n\nIntroduction\nDeep learning systems have shown a lot of promise for extractive Question Answering (QA), with performance comparable to humans when ... | [
"Unanswerable"
] | 3,900 | qasper |
1f23a09c-9ea8-4baf-a613-b25b6a73a2dc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they define robustness of a model?\n\nIntroduction\nWe posses a wealth of prior knowledge about many natural language processing tasks. For example, in text categorization, we know that words such as NBA, player, and basketball... | [
"Low sensitivity to bias in prior knowledge"
] | 5,001 | qasper |
35656c76-d051-450a-8a10-c3eb93a2a951 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the word level baseline they compare to?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be absent or occur in low frequency. Estimating th... | [
"a simple word-level encoder, with the input as words instead of characters"
] | 3,479 | qasper |
57d445b2-bcca-4511-b561-a7e796d4d091 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"By how much do they improve the efficacy of the attention mechanism?\n\nIntroduction\nThe use of RNNs in the field of Statistical Machine Translation (SMT) has revolutionised the approaches to automated translation. As opposed to trad... | [
"Unanswerable"
] | 6,994 | qasper |
5df0e038-de32-4158-b355-a961971c4f69 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the reported agreement for the annotation?\n\nIntroduction\nCancer is one of the leading causes of death in the world, with over 80,000 deaths registered in Canada in 2017 (Canadian Cancer Statistics 2017). A computer-aided sy... | [
"Unanswerable"
] | 2,758 | qasper |
6079b769-8aaa-4c0b-9b8e-fa92d0ff977f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different characters were in dataset?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BIBREF0. This is largely due to in... | [
"45,821 characters"
] | 7,237 | qasper |
6914af83-f9da-4d81-a63b-8c0024428ed6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How did they determine fake news tweets?\n\n10pt\n1.10pt\n[ Characterizing Political Fake News in Twitter by its Meta-DataJulio Amador Díaz LópezAxel Oehmichen Miguel Molina-Solana( j.amador, axelfrancois.oehmichen11, mmolinas@imperia... | [
"Exposure, Characterization, Polarization"
] | 3,928 | qasper |
6d9368d9-0afe-42c0-a476-13a863def3e4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the average length of the title text?\n\nIntroduction\nThe distribution of textual content is typically very fast and catches user attention for only a short period of time BIBREF0 . For this reason, proper wording of the arti... | [
"Unanswerable"
] | 3,081 | qasper |
6f9187f0-39dc-47b0-94a4-aaa73e0d486b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets do they use?\n\nIntroduction\nAdversarial examples, a term introduced in BIBREF0, are inputs transformed by small perturbations that machine learning models consistently misclassify. The experiments are conducted in the ... | [
"three datasets based on IMDB reviews and Yelp reviews"
] | 6,094 | qasper |
79846790-0d43-4a8c-a7f6-94b469621cea | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How effective is their NCEL approach overall?\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), ma... | [
"NCEL consistently outperforms various baselines with a favorable generalization ability"
] | 5,745 | qasper |
7fb0e6dd-8247-47b6-965d-655365a58220 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is the difference in performance between proposed model and baselines?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BI... | [
"Metric difference between Aloha and best baseline score:\nHits@1/20: +0.061 (0.3642 vs 0.3032)\nMRR: +0.0572(0.5114 vs 0.4542)\nF1: -0.0484 (0.3901 vs 0.4385)\nBLEU: +0.0474 (0.2867 vs 0.2393)"
] | 7,243 | qasper |
8e7bfaf9-f00c-42ed-9280-4daabd832254 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did they pefrorm any cross-lingual vs single language evaluation?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding systems for politi... | [
"Yes"
] | 5,006 | qasper |
a0b9f236-a4f7-4f69-8baa-124309d0d71a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is an instance a sentence or an IE tuple?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the requisite domain ... | [
"sentence"
] | 5,761 | qasper |
a907bab8-345b-4540-aad4-3dd19486fc00 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How is sensationalism scorer trained?\n\nIntroduction\nHeadline generation is the process of creating a headline-style sentence given an input article. The research community has been regarding the task of headline generation as a sum... | [
"by classifying sensational and non-sensational headlines using a one-layer CNN with a binary cross entropy loss $L_{\\text{sen}}$"
] | 6,345 | qasper |
b131d133-fbdd-4ee3-8cc3-d03459a9ae07 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which datasets do they use?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativecommons.org/licenses/by/4.0/\nEntity linking (EL), mapping entity menti... | [
"CoNLL-YAGO, TAC2010, ACE2004, AQUAINT, WW"
] | 5,742 | qasper |
b259474f-4c36-4a10-8cfa-ebac1ce73b8c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What in-domain text did they use?\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-domain text... | [
"PubMed+PMC (the data used for BioBERTv1.0) and/or CORD-19 (Covid-19 Open Research Dataset)"
] | 5,062 | qasper |
b31f9621-b70b-4c95-9f01-c5d691a00682 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"On how many language pairs do they show that preordering assisting language sentences helps translation quality?\n\nIntroduction\nDeep Learning approaches have achieved impressive results on various NLP tasks BIBREF0 , BIBREF1 , BIBRE... | [
"Bengali, Gujarati, Marathi, Malayalam and Tamil are the primary source languages, and translation from these to Hindi constitute the child tasks."
] | 2,985 | qasper |
b39c0ecd-6ec3-4caa-8f1b-ba5e79eeaf28 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which non-english language had the best performance?\n\nIntroduction\nWith the steady growth in the commercial websites and social media venues, the access to users' reviews have become easier. As the amount of data that can be mined ... | [
"Russsian"
] | 3,544 | qasper |
b3cc296a-9665-4133-be61-ffc7b5022ce7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What transfer learning tasks are evaluated?\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 s... | [
"MR, CR, SUBJ, MPQA, SST, TREC, MRPC"
] | 5,615 | qasper |
c26cc6b2-095a-44bf-af9b-ae0b4d41b79c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which pretrained word vectors did they use?\n\nIntroduction\nThe distribution of textual content is typically very fast and catches user attention for only a short period of time BIBREF0 . For this reason, proper wording of the articl... | [
"GloVe word vectors BIBREF16 pre-trained on two datasets: Wikipedia 2014 with Gigaword5 (W+G5) and Common Crawl (CC)"
] | 3,079 | qasper |
c334e6bc-753c-4e20-9dbf-53263d21adc8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the two neural embedding models?\n\nIntroduction\nVector-based semantic mapping models are used to represent textual structures (words, phrases, and documents) as high-dimensional meaning vectors. Typically, these models util... | [
"Concept Raw Context model, Concept-Concept Context model"
] | 5,385 | qasper |
c3ff4c49-73f1-4132-9a05-5762c7f68da8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which variation provides the best results on this dataset?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassm... | [
"the model with multi-attention mechanism and a projected layer"
] | 3,868 | qasper |
c6e5a463-f7c6-46dc-b9bf-afc90c7c24db | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets do they evaluate on?\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 dat... | [
"Unanswerable"
] | 5,842 | qasper |
c74b032d-9ba8-4ddc-888e-4548c2fc6039 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline approaches does this approach out-perform?\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 becom... | [
"K-means, LEM, DPEMM"
] | 5,497 | qasper |
caf8754b-1469-482f-a263-1c1832cae59e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which sentiment class is the most accurately predicted by ELS systems?\n\nIntroduction\nAs social media, specially Twitter, takes on an influential role in presidential elections in the U.S., natural language processing of political t... | [
"neutral sentiment"
] | 2,141 | qasper |
cee335e9-4322-43fd-8f16-428bf7d52c81 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What clustering algorithms were used?\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 process e... | [
"simple clustering algorithm which uses the cosine similarity between word embeddings"
] | 4,193 | qasper |
de9379fb-04e5-4269-888a-6880076ac80b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does this method help in sentiment classification task improvement?\n\nIntroduction\nThe NLP community is revisiting the role of linguistic structure in applications with the advent of contextual word representations (cwrs) derived fr... | [
"Yes"
] | 3,683 | qasper |
e146a460-eb8b-48b6-941b-5580e2414120 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use graphical models?\n\nIntroduction\nFollowing developing news stories is imperative to making real-time decisions on important political and public safety matters. Given the abundance of media providers and languages, this ... | [
"No"
] | 4,220 | qasper |
e5c0f0f2-3cd6-4cc5-901b-5f5891df039c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"by how much did their model improve?\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 pe... | [
"6.37 BLEU"
] | 3,186 | qasper |
e9f03e9c-0034-4845-8ce9-5eca5ae25722 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their model improve interpretability compared to softmax transformers?\n\nIntroduction\nThe Transformer architecture BIBREF0 for deep neural networks has quickly risen to prominence in NLP through its efficiency and performan... | [
"the attention heads in the proposed adaptively sparse Transformer can specialize more and with higher confidence"
] | 7,823 | qasper |
eb4c68ab-8871-4565-ad49-5ef64874813a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines do they compare with?\n\nIntroduction\nThere exists a class of language construction known as pun in natural language texts and utterances, where a certain word or other lexical items are used to exploit two or more sep... | [
"They compare with the following models: by Pedersen (2017), by Pramanick and Das (2017), by Mikhalkova and Karyakin (2017), by Vadehra (2017), Indurthi and Oota (2017), by Vechtomova (2017), by (Cai et al., 2018), and CRF."
] | 3,834 | qasper |
f3258da5-4ac6-422d-b11b-b74c31f499a6 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many annotators tagged each text?\n\nIntroduction\n“Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various languages, cultures, ag... | [
"three annotators"
] | 3,609 | qasper |
0b2132a4-1dca-4be8-ab19-bab390d06ac5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is pre-training effective in their evaluation?\n\nIntroduction\nRecently, neural machine translation (NMT) has gained popularity in the field of machine translation. The conventional encoder-decoder NMT proposed by Cho2014 uses two re... | [
"Yes"
] | 3,067 | qasper |
0ef8e992-4c24-47c7-a387-3b3cebbd5c1a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"why are their techniques cheaper to implement?\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 tak... | [
"They use a slightly modified copy of the target to create the pseudo-text instead of full BT to make their technique cheaper"
] | 5,628 | qasper |
19529347-5133-437b-b955-bb9a4d22ccfc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are previous state of the art results?\n\nIntroduction\nNamed entity recognition (NER) is a challenging problem in Natural Language Processing, and often serves as an important step for many popular applications, such as informat... | [
"For Named entity the maximum precision was 66.67%, and the average 62.58%, same values for Recall was 55.97% and 50.33%, and for F1 57.14% and 55.64%. Where for Nominal Mention had maximum recall of 74.48% and average of 73.67%, Recall had values of 54.55% and 53.7%, and F1 had values of 62.97% and 62.12%. Final... | 2,382 | qasper |
1f0087c0-62b4-4dec-a4ad-bc4762a3c202 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does proposed qualitative annotation schema looks like?\n\nIntroduction\nThere is a recent spark of interest in the task of Question Answering (QA) over unstructured textual data, also referred to as Machine Reading Comprehension ... | [
"The resulting taxonomy of the framework is shown in Figure FIGREF10"
] | 6,561 | qasper |
2b559835-1af3-4d3f-8b66-4deb6a9ba8b5 | [{"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... | [
"Answer with content missing: (Whole Method and Results sections) Self-paced reading times widely benefit ERP prediction, while eye-tracking data seems to have more limited benefit to just the ELAN, LAN, and PNP ERP components.\nSelect:\n- ELAN, LAN\n- PNP ERP"
] | 2,373 | qasper |
2feadd32-6dd6-472c-a1e4-6142c44c26b0 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the authors conduct experiments on the tasks mentioned?\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 f... | [
"No"
] | 3,343 | qasper |
38a4ba94-9387-45cc-b8d6-dc8969fdd5b4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline?\n\nIntroduction\nThe apparent rise in political incivility has attracted substantial attention from scholars in recent years. These studies have largely focused on the extent to which politicians and elected off... | [
"stochastic gradient descent, naive bayes, decision tree"
] | 4,408 | qasper |
3a86cc86-164a-4fd9-aea0-aa24816b0625 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they experiment with their proposed model on any other dataset other than MovieQA?\n\nIntroduction\nMany machine learning models in question answering tasks often involve matching mechanism. For example, in factoid question answeri... | [
"Yes"
] | 3,278 | qasper |
3c85f2e5-2498-4218-9b53-f8b046043d63 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much better than the baseline is LiLi?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural language processing. Early such systems were mostly built using markup languages ... | [
"In case of Freebase knowledge base, LiLi model had better F1 score than the single model by 0.20 , 0.01, 0.159 for kwn, unk, and all test Rel type. The values for WordNet are 0.25, 0.1, 0.2. \n"
] | 8,580 | qasper |
4371d5d4-11b1-4bc6-b876-8988d20df202 | [{"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.... | [
"Unanswerable"
] | 5,674 | qasper |
4d4285a8-9a88-4c7f-9904-71b918cb67fb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did ensemble schemes help in boosting peformance, by how much?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and aim individu... | [
"They increased F1 Score by 0.029 in Sentence Level Classification, and by 0.044 in Fragment-Level classification"
] | 2,441 | qasper |
508ea54f-3098-4ab5-9d03-189029508bf1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they determine if tweets have been used by journalists?\n\nIntroduction\nSocial media is now becoming an important real-time information source, especially during natural disasters and emergencies. It is now very common for tra... | [
" we look into the archived snapshots of two major news websites (CNN, NBC), and then extract the tweet blocks that are embedded in the news articles"
] | 4,650 | qasper |
519315a8-a543-4e13-9733-a4e47a1f1303 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are models evaluated in this human-machine communication game?\n\nIntroduction\nSuppose a user wants to write a sentence “I will be 10 minutes late.” Ideally, she would type just a few keywords such as “10 minutes late” and an aut... | [
"by training an autocomplete system on 500K randomly sampled sentences from Yelp reviews"
] | 2,586 | qasper |
57a88622-42c8-45fb-918f-3d5324fc4899 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nWith the availability of rich data on users' locations, profiles and search history, personalization has become the leading trend in large-scale information retrieval. Howe... | [
"Unanswerable"
] | 10,186 | qasper |
61ebcbf4-fb1b-430a-9935-6f9b26a18e34 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where did the texts in the corpus come from?\n\nIntroduction\n“Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various languages, cultu... | [
"tweets from the past two years from domains like `sports', `politics', `entertainment'"
] | 3,611 | qasper |
66ec89ec-3d17-45f9-ac19-a0025148cdeb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which multiple datasets did they train on during joint training?\n\nIntroduction\nThe task of speculation detection and scope resolution is critical in distinguishing factual information from speculative information. This has multiple... | [
"BioScope Abstracts, SFU, and BioScope Full Papers"
] | 3,292 | qasper |
67b8ab1b-7749-471b-9948-8269077b427f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the GhostVLAD approach?\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-... | [
"An extension of NetVLAD which replaces hard assignment-based clustering with soft assignment-based clustering with the additon o fusing Ghost clusters to deal with noisy content."
] | 3,268 | qasper |
70d43c33-12a1-4fd0-be34-768e81ac4752 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baseline systems?\n\nIntroduction\nWe participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs: English INLINEFORM0 Czech, English INLINEFORM1 German, Englis... | [
"attentional encoder-decoder networks BIBREF0"
] | 2,989 | qasper |
77ba66e2-3cc9-4e08-bce7-1cc4510a5c16 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the components of the general knowledge learning engine?\n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural language processing. Early such systems were mostly built ... | [
"Knowledge Store (KS) , Knowledge Graph ( INLINEFORM0 ), Relation-Entity Matrix ( INLINEFORM2 ), Task Experience Store ( INLINEFORM15 ), Incomplete Feature DB ( INLINEFORM29 )"
] | 8,581 | qasper |
7b6e1544-aafa-481e-a6c8-4b2b2606c8c4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\n\nIntroduction\nAutomatic summarization has enjoyed wide popularity in natural language processing due to its potential for various information access applications. Examples include tools which aid users navig... | [
"Unanswerable"
] | 3,864 | qasper |
872818ca-0665-4809-99f4-639e87777507 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do they obtain psychological dimensions of people?\n\nIntroduction\nBlogging gained momentum in 1999 and became especially popular after the launch of freely available, hosted platforms such as blogger.com or livejournal.com. Blog... | [
"using the Meaning Extraction Method"
] | 1,934 | qasper |
89def187-e326-4c27-b0e2-3fcfc64bb1a5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance of their method?\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 automa... | [
"Unanswerable"
] | 5,731 | qasper |
8b5e6e99-ea6b-45e7-bb30-a29627fdacf5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is their definition of tweets going viral?\n\n10pt\n1.10pt\n[ Characterizing Political Fake News in Twitter by its Meta-DataJulio Amador Díaz LópezAxel Oehmichen Miguel Molina-Solana( j.amador, axelfrancois.oehmichen11, mmolinas@... | [
"those that contain a high number of retweets"
] | 3,929 | qasper |
8d68fe22-9dd6-4824-be18-70423fd120e8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does dataset model character's profiles?\n\nIntroduction\nAttempts toward constructing human-like dialogue agents have met significant difficulties, such as maintaining conversation consistency BIBREF0. This is largely due to inab... | [
"attributes are determined by human viewers and their impressions of the characters, and are correlated with human-like characteristics"
] | 7,237 | qasper |
93051ad4-0386-4816-b99e-82709253a7ca | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What participating systems had better results than ones authors submitted?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and ... | [
"For SLC task : Ituorp, ProperGander and YMJA teams had better results.\nFor FLC task: newspeak and Antiganda teams had better results."
] | 2,439 | qasper |
968b7e65-caa2-403b-b664-ea3f1aff1ba8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are method improvements of F1 for paraphrase identification?\n\nIntroduction\nData imbalance is a common issue in a variety of NLP tasks such as tagging and machine reading comprehension. Table TABREF3 gives concrete examples: fo... | [
"Using DSC loss improves the F1 score by +0.58 for MRPC and +0.73 for QQP"
] | 5,641 | qasper |
96f09b6f-ffc6-46b8-b05f-4405e5ebcd51 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the datasets used for evaluation?\n\nIntroduction\nLanguage model pretraining has advanced the state of the art in many NLP tasks ranging from sentiment analysis, to question answering, natural language inference, named entit... | [
"the CNN/DailyMail news highlights dataset BIBREF24, the New York Times Annotated Corpus (NYT; BIBREF25), XSum BIBREF22"
] | 6,516 | qasper |
9dc1517e-1964-4add-876f-22ba1d00ae70 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What useful information does attention capture?\n\nIntroduction\nNeural machine translation (NMT) has gained a lot of attention recently due to its substantial improvements in machine translation quality achieving state-of-the-art per... | [
"Alignment points of the POS tags."
] | 4,376 | qasper |
a552989b-c01c-4902-8c2c-258a2ff3ef39 | [{"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... | [
"By conducting a survey among engineers"
] | 2,372 | qasper |
a5a26f6b-8ea7-47ee-919b-389997024bd4 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Who are the crowdworkers?\n\nIntroduction\nAs social media, specially Twitter, takes on an influential role in presidential elections in the U.S., natural language processing of political tweets BIBREF0 has the potential to help with ... | [
"people in the US that use Amazon Mechanical Turk"
] | 2,134 | qasper |
b7c6f70c-9d72-4471-9503-e74a2369b01c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How are the siamese networks trained?\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 sentenc... | [
"Unanswerable"
] | 5,617 | qasper |
d1fdd609-a294-4319-9df5-e7d666638539 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which variant of the recurrent neural network do they use?\n\nIntroduction\nRelation classification is the task of assigning sentences with two marked entities to a predefined set of relations. The sentence “We poured the <e1>milk</e1... | [
"uni-directional RNN"
] | 3,320 | qasper |
e6e69d1f-2287-4b46-9ba4-b780853e6fca | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Did ensemble schemes help in boosting peformance, by how much?\n\nIntroduction\nIn the age of information dissemination without quality control, it has enabled malicious users to spread misinformation via social media and aim individu... | [
"The best ensemble topped the best single model by 0.029 in F1 score on dev (external)."
] | 2,441 | qasper |
e7099c23-3632-4e59-b68e-d7aae3ca050e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they use large or small BERT?\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 word in a par... | [
"small BERT"
] | 3,003 | qasper |
e7e679ff-a729-44f3-9e26-cbf987a0996d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many tweets did they collect?\n\nIntroduction\nStance detection (also called stance identification or stance classification) is one of the considerably recent research topics in natural language processing (NLP). It is usually def... | [
"700"
] | 2,821 | qasper |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.