uniq_id
stringlengths
36
36
messages
stringlengths
2.65k
180k
answers
listlengths
1
1
num_tokens
int64
507
32.7k
task
stringclasses
7 values
10f3dcd8-9621-49d1-a142-6c7794c51c8e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which demographic dimensions of people do they obtain?\n\nIntroduction\nBlogging gained momentum in 1999 and became especially popular after the launch of freely available, hosted platforms such as blogger.com or livejournal.com. Blog...
[ "occupation, industry, profile information, language use, gender " ]
1,934
qasper
2581d310-9457-47bb-b710-5ed95a2f8a73
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they compare human-level performance to model performance for their dataset?\n\nIntroduction\nProgress in AI has been driven by, among other things, the development of challenging large-scale benchmarks like ImageNet BIBREF0 in com...
[ "No" ]
6,708
qasper
26b274df-d768-449c-a8bc-a169f0c6b9ba
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metric is used?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known then the ap...
[ "average classification accuracy, execution performance" ]
2,608
qasper
3660273b-5247-407b-861c-e7913ce5071f
[{"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...
[ "No" ]
4,294
qasper
4156e04b-24cc-44af-9059-1493645828a6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which existing benchmarks did they compare to?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nIn the spirit of the b...
[ " Affective Text dataset, Fairy Tales dataset, ISEAR dataset" ]
4,373
qasper
487bb69f-3b67-4732-a5dd-9c3537346ea4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which dataset do they use?\n\nIntroduction\nConventional large-vocabulary continuous speech recognition (LVCSR) systems typically perform multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of ...
[ "WSJ-SI84, WSJ-SI284" ]
3,652
qasper
495bac30-4401-4aa0-ae7c-4f525d9cd20b
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why masking words in the decoder is helpful?\n\nIntroduction\nText summarization generates summaries from input documents while keeping salient information. It is an important task and can be applied to several real-world applications...
[ "ecause this process is similar to the cloze task in BERT's pre-train process, therefore by using the ability of the contextual language model the decoder can generate more fluent and natural sequences." ]
5,688
qasper
5359ef36-a93d-4412-9c94-097611998a30
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What existing approaches do they compare to?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interac...
[ "Waseem and Hovy BIBREF5, Davidson et al. BIBREF9, Waseem et al. BIBREF10" ]
5,698
qasper
54b12166-1899-4253-a934-f375104a3f6c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of out-of-domain data?\n\nIntroduction\nAssembling training corpora of annotated natural language examples in specialized domains such as biomedicine poses considerable challenges. Experts with the requisite domain knowledge...
[ "Unanswerable" ]
5,759
qasper
58a62347-332c-4fb7-b604-248e20996fc2
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which benchmark datasets are used?\n\nIntroduction\nSarcasm is defined as “a sharp, bitter, or cutting expression or remark; a bitter gibe or taunt”. As the fields of affective computing and sentiment analysis have gained increasing p...
[ "This dataset was created by BIBREF8, another English dataset from BIBREF8 , dataset from The Sarcasm Detector" ]
6,598
qasper
5a9454e8-357e-489e-8699-7d4d9f90e0d0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does car speak pertains to a car's physical attributes?\n\nIntroduction\nA large portion of the car-buying experience in the United States involves interactions at a car dealership BIBREF0, BIBREF1, BIBREF2. Traditionally, a car d...
[ "we do not know exactly" ]
2,209
qasper
624133b7-d3fc-41c6-87f5-34c5f732583d
[{"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 ...
[ "FIGREF10" ]
6,561
qasper
7938894f-1531-4967-a33b-038d7cb91495
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the experiments focus on a specific domain?\n\nIntroduction\nFrom a group of small users at the time of its inception in 2009, Quora has evolved in the last few years into one of the largest community driven Q&A sites with divers...
[ "No" ]
2,008
qasper
7c5af4fb-8381-41c6-a880-72d074b7816c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they demonstrate why interdisciplinary insights are important?\n\nIntroduction\nIn June 2015, the operators of the online discussion site Reddit banned several communities under new anti-harassment rules. BIBREF0 used this opportun...
[ "No" ]
10,570
qasper
7f9d90cb-18e4-4221-b950-fb5546ef5c81
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do the backoff strategies work?\n\nIntroduction\nDespite the rapid progress of deep learning techniques on diverse supervised learning tasks, these models remain brittle to subtle shifts in the data distribution. Even when the per...
[ "Backoff to \"a\" when an UNK-predicted word is encountered, backoff to a more generic word recognition model when the model predicts UNK" ]
5,902
qasper
a4b60df3-f74b-49f5-a03e-1a645f8e31b6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is a bifocal attention mechanism?\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, furnitu...
[ "At the macro level, it is important to decide which is the appropriate field to attend to next, micro level (i.e., within a field) it is important to know which values to attend to next, fuse the attention weights at the two levels" ]
5,868
qasper
aa65917e-8659-4370-8c99-78a12fd04b98
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What methods were used for sentence classification?\n\nIntroduction\nPerformance appraisal (PA) is an important HR process, particularly for modern organizations that crucially depend on the skills and expertise of their workforce. Th...
[ "Logistic Regression, Multinomial Naive Bayes, Random Forest, AdaBoost, Linear SVM, SVM with ADWSK and Pattern-based" ]
4,195
qasper
ad8cc651-9ee0-4dc6-b093-80504ea9cbcf
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the organic and inorganic ways to show political affiliation through profile changes?\n\nIntroduction\nUser profiles on social media platforms serve as a virtual introduction of the users. People often maintain their online p...
[ "Organic: mention of political parties names in the profile attributes, specific mentions of political handles in the profile attributes.\nInorganic: adding Chowkidar to the profile attributes, the effect of changing the profile attribute in accordance with Prime Minister's campaign, the addition of election campa...
6,816
qasper
b6c4c85c-f545-4efe-b3e4-91fa7eceda97
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments do they use to quantify the extent of interpretability?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building b...
[ "Human evaluation for interpretability using the word intrusion test and automated evaluation for interpretability using a semantic category-based approach based on the method and category dataset (SEMCAT)." ]
8,087
qasper
bd5e8ee0-fa35-4212-928a-9b3d2e4d841a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which of the three pretraining tasks is the most helpful?\n\nIntroduction\nLarge pre-trained language models BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4 improved the state-of-the-art of various natural language understanding (NLU) tas...
[ "SR" ]
6,839
qasper
bed43770-1a9f-492e-8fe0-e0101d6abff7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which translation systems do they compare against?\n\nIntroduction\nNumerous lexical semantic properties are captured by representations encoding distributional properties of words, as has been demonstrated in a variety of tasks BIBRE...
[ "hierarchical phrase-based system BIBREF29, appropriate additional baseline would be to mark translation rules with these indicator functions but without the scores, akin to identifying rules with phrases in them (Baseline + SegOn)" ]
5,397
qasper
c44fb4a2-cec8-45e6-bf0b-652807602f2d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is model compactness measured?\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...
[ "15.4 MB" ]
4,277
qasper
c91c5790-487f-4e51-9bee-956617b9db1d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What datasets did they use for evaluation?\n\nIntroduction\nBidirectional Encoder Representations from Transformers (BERT) is a novel Transformer BIBREF0 model, which recently achieved state-of-the-art performance in several language ...
[ "CSAT dataset , 20 newsgroups, Fisher Phase 1 corpus" ]
3,709
qasper
d50d45fd-8077-4b84-9204-94533bbbfdca
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they remove seasonality from the time series?\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...
[ "Unanswerable" ]
3,164
qasper
d9b22e76-62c8-46fb-bdf3-48c3645404b5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they analyze specific derogatory words?\n\nKeywords:\ncomputational sociolinguistics, dehumanization, lexical variation, language change, media, New York Times, LGBTQ\nWarning: this paper contains material that some may find offens...
[ "Yes" ]
17,774
qasper
dbf89d1d-3306-455f-b700-8051e80e33c5
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which component is the least impactful?\n\nIntroduction\nThe concept of message passing over graphs has been around for many years BIBREF0, BIBREF1, as well as that of graph neural networks (GNNs) BIBREF2, BIBREF3. However, GNNs have ...
[ "Based on table results provided changing directed to undirected edges had least impact - max abs difference of 0.33 points on all three datasets." ]
6,274
qasper
eca3a2f0-d8f3-4d7a-a234-ff3000ffc544
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how was the data collected?\n\nIntroduction\nAmbiguity and implicitness are inherent properties of natural language that cause challenges for computational models of language understanding. In everyday communication, people assume a s...
[ "The data was collected using 3 components: describe a series of pilot studies that were conducted to collect commonsense inference questions, then discuss the resulting data collection of questions, texts and answers via crowdsourcing on Amazon Mechanical Turk and gives information about some necessary postprocess...
5,793
qasper
edfd9a2d-3ccd-4ec8-96b0-baf59e3c6e7d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What do they mean by a person's industry?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friends a...
[ "the aggregate of enterprises in a particular field" ]
5,300
qasper
fa9a5742-6b33-4a81-ad20-33f52292af9e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Based on this paper, what is the more predictive set of features to detect fake news?\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 ...
[ "words embeddings, style, and morality features" ]
2,893
qasper
0410ea38-a7d7-49ce-82ef-4d719627d627
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the previous state-of-the-art in summarization?\n\nIntroduction\nPre-training of language models has been shown to provide large improvements for a range of language understanding tasks BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . ...
[ "BIBREF26" ]
2,672
qasper
22f635e4-8415-4189-aa5d-16734e38755f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many training samples do you have for training?\n\nIntroduction\nFrom a group of small users at the time of its inception in 2009, Quora has evolved in the last few years into one of the largest community driven Q&A sites with div...
[ "Unanswerable" ]
2,009
qasper
2880fb10-7ded-4c69-863c-6b0a52cd47ac
[{"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-...
[ "extension of the NetVLAD, adds Ghost clusters along with the NetVLAD clusters" ]
3,268
qasper
2db96e7e-5687-4140-b6e3-08edd804a9d8
[{"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...
[ "twitter" ]
3,611
qasper
3b1db734-e83c-4f53-94bb-65ac958509df
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which Facebook pages did they look at?\n\nIntroduction\nThis work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nIn the spirit of the brevity o...
[ "FoxNews, CNN, ESPN, New York Times, Time magazine, Huffington Post Weird News, The Guardian, Cartoon Network, Cooking Light, Home Cooking Adventure, Justin Bieber, Nickelodeon, Spongebob, Disney." ]
4,373
qasper
40ddf929-b182-4a40-8e30-b1d685dfd453
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other political events are included in the database?\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 t...
[ "US presidential primaries, Democratic and Republican National Conventions" ]
4,413
qasper
414db716-bd7b-4e7e-87f0-53703d068418
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What tasks were evaluated?\n\nIntroduction\nA large majority of the human knowledge is recorded through text documents. That is why ability for a system to automatically infer information from text without any structured data has beco...
[ "Detection of an aspect in a review, Prediction of the customer general satisfaction, Prediction of the global trend of an aspect in a given review, Prediction of whether the rating of a given aspect is above or under a given value, Prediction of the exact rating of an aspect in a review, Prediction of the list of ...
4,699
qasper
53312cc0-bcb7-45be-bc52-8b0a4f9ae8a0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the additive modification to the objective function?\n\nIntroduction\nDistributed word representations, commonly referred to as word embeddings BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , serve as elementary building blocks in the...
[ "An additive term added to the cost function for any one of the words of concept word-groups" ]
8,084
qasper
53cc3959-0ceb-4aa7-ab2d-ab6adae74b06
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they study numerical properties of their obtained vectors (such as orthogonality)?\n\nIntroduction\nNumerous lexical semantic properties are captured by representations encoding distributional properties of words, as has been demon...
[ "No" ]
5,406
qasper
58b23715-e902-47d1-add1-3f419796f889
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the sources of the datasets?\n\nIntroduction\nFollowing developing news stories is imperative to making real-time decisions on important political and public safety matters. Given the abundance of media providers and language...
[ "rupnik2016news, Deutsche Welle's news website" ]
4,222
qasper
5d0b6428-ee78-4170-8521-924ef0575402
[{"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...
[ "No" ]
6,569
qasper
5e24842e-93e9-423d-bdf6-140041098b97
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What social media platform did they look at?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friend...
[ "http://www.blogger.com" ]
5,299
qasper
6358b667-ef21-48b7-a958-78f00fc5d52e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the models used for the baseline of the three NLP tasks?\n\nIntroduction\nRecent years have seen unprecedented progress for Natural Language Processing (NLP) on almost every NLP subtask. Even though low-resource settings have...
[ "For speech synthesis, they build a speech clustergen statistical speech synthesizer BIBREF9. For speech recognition, they use Kaldi BIBREF11. For Machine Translation, they use a Transformer architecture from BIBREF15." ]
4,184
qasper
7d3dfdda-97b1-4e28-ba00-d7925859fcb6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many subjects does the EEG data come from?\n\nIntroduction\nDecoding intended speech or motor activity from brain signals is one of the major research areas in Brain Computer Interface (BCI) systems BIBREF0 , BIBREF1 . In particul...
[ "14 participants" ]
3,283
qasper
8146e3fb-6dfd-4bd6-95ad-aa79fc4d9cae
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Can their indexing-based method be applied to create other QA datasets in other domains, and not just Wikipedia?\n\nIntroduction\nQuestion answering (QA) has been a blooming research field for the last decade. Selection-based QA impli...
[ "Unanswerable" ]
2,616
qasper
842a3cc5-47ac-418c-8156-b6f6ddc07586
[{"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, IWSLT 2017 German $\\rightarrow $ English BIBREF27, KFTT Japanese $\\rightarrow $ English BIBREF28, WMT 2016 Romanian $\\rightarrow $ English BIBREF29, WMT 2014 English $\\rightarrow $ German BIBREF30" ]
7,818
qasper
94c04548-559f-4e75-968c-31786b8dfb9e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Was PolyReponse evaluated against some baseline?\n\nIntroduction and Background\nTask-oriented dialogue systems are primarily designed to search and interact with large databases which contain information pertaining to a certain dialo...
[ "No" ]
3,846
qasper
9b76190f-fe01-4d42-a91b-53ccda906299
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is it valid to presume a bad medical wikipedia article should not contain much domain-specific jargon?\n\nIntroduction\nAs observed by a recent article of Nature News BIBREF0 , “Wikipedia is among the most frequently visited websites ...
[ "No" ]
6,204
qasper
a48f09df-bd40-4281-9f8a-091ca16bcd8f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What were the datasets used in this paper?\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...
[ "The dataset from the SociaL Media And Harassment Competition of the ECML PKDD 2019 Conference. " ]
3,867
qasper
a8046fff-e293-4d9b-8022-0bd68bd5d258
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Where do they obtain the news videos from?\n\nIntroduction\nThe distribution of textual content is typically very fast and catches user attention for only a short period of time BIBREF0 . For this reason, proper wording of the article...
[ "NowThisNews Facebook page" ]
3,080
qasper
a8c04b15-7f71-40ed-8aa1-a66fbd0f1181
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the two large-scale datasets used?\n\nIntroduction and related work\nIn recent years there has been increasing interest on the issue of disinformation spreading on online social media. Global concern over false (or \"fake\") ...
[ "US dataset, Italian dataset" ]
6,629
qasper
aa5ff0cf-ac68-47f8-8515-a63782f289b3
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other models do they compare to?\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 lang...
[ "SAN Baseline, BNA, DocQA, R.M-Reader, R.M-Reader+Verifier and DocQA+ELMo" ]
2,439
qasper
b016fc51-d11c-45ce-b65b-b1f810846c47
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What classification baselines are used for comparison?\n\nIntroduction\nIn recent years, word embeddings have been successfully used in natural language processing (NLP), the most commonly known models are Word2Vec BIBREF0 and GloveBI...
[ "VAE based phone classification" ]
5,207
qasper
b16e2887-77a8-48d3-afd5-7f9f84c117c1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the G-BERT model useful beyond the task considered?\n\nIntroduction\nThe availability of massive electronic health records (EHR) data and the advances of deep learning technologies have provided unprecedented resource and opportuni...
[ "It learns a representation of medical records. The learned representation (embeddings) can be used for other predictive tasks involving information from electronic health records." ]
6,110
qasper
b9745478-56fd-41be-a9dc-5492495714ec
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which information about typography is included in the corpus?\n\nIntroduction\nSimplified language is a variety of standard language characterized by reduced lexical and syntactic complexity, the addition of explanations for difficult...
[ "font type, font style, Information on the font type and font style (e.g., italics, bold print) of a token and its position on the physical page" ]
3,693
qasper
c6334c62-730a-453b-b8ea-d78ccc35e165
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper report the performance of the model for each individual language?\n\nIntroduction\nIn recent years many datasets have been created for the task of automated stance detection, advancing natural language understanding sys...
[ "Unanswerable" ]
5,004
qasper
d1f4fc48-2f9c-4719-866b-c8071edffc0c
[{"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...
[ "we also use two of its adversarial sets, namely AddSent and AddOneSent BIBREF6 , to evaluate the robustness to noise" ]
5,694
qasper
d81e95da-9c1f-4867-afa2-56d617c633cc
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which publicly available datasets are used?\n\nIntroduction\nPeople are increasingly using social networking platforms such as Twitter, Facebook, YouTube, etc. to communicate their opinions and share information. Although the interact...
[ "Waseem-dataset, Davidson-dataset," ]
5,697
qasper
d86cf90c-6d99-4659-86d5-5e3e719254a1
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baselines did they consider?\n\nIntroduction\nExplanations of happenings in one's life, causal explanations, are an important topic of study in social, psychological, economic, and behavioral sciences. For example, psychologists ...
[ "state-of-the-art PDTB taggers" ]
5,199
qasper
d89d62bf-de5d-4f63-a329-e70ff4aec747
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the paper clearly establish that the challenges listed here exist in this dataset and task?\n\nIntroduction\nWe understand from Zipf's Law that in any natural language corpus a majority of the vocabulary word types will either be...
[ "Yes" ]
3,486
qasper
db604a74-3855-4737-b9be-dae0a85eef9c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset do they use to evaluate their method?\n\nIntroduction\nAntonymy and synonymy represent lexical semantic relations that are central to the organization of the mental lexicon BIBREF0 . While antonymy is defined as the oppos...
[ "English Wikipedia dump from June 2016" ]
5,402
qasper
e7b5f992-cf03-4d74-9b4b-05e4dbe2eaa0
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what were the baselines?\n\nIntroduction\nEmotion detection has long been a topic of interest to scholars in natural language processing (NLP) domain. Researchers aim to recognize the emotion behind the text and distribute similar one...
[ "BOW-LR, BOW-RF. TFIDF-RF, TextCNN, C-TextCNN" ]
4,510
qasper
ea991043-f4bd-4373-8ec8-644f3270f794
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their ensemble method work?\n\nIntroduction\nSince humans amass more and more generally available data in the form of unstructured text it would be very useful to teach machines to read and comprehend such data and then use t...
[ "simply averaging the predictions from the constituent single models" ]
5,270
qasper
eeea5ae6-a896-49bf-b46c-d52bd45512b8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline method is 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 reviewers on a topic or an...
[ "using word2vec to create features that are used as input to the SVM" ]
5,002
qasper
f86467eb-7a81-4bfa-9af5-1f55a5e5ff90
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What embeddings are used?\n\nIntroduction\nTo appear in Proceedings of International Workshop on Health Intelligence (W3PHIAI) of the 34th AAAI Conference on Artificial Intelligence, 2020.\nPhysician burnout is a growing concern, esti...
[ "ELMO BIBREF11, BERT BIBREF12 and ClinicalBERT BIBREF13" ]
6,487
qasper
01a8f03e-958f-4e23-aaf5-87c1d8440e31
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big was the corpora they trained ELMo on?\n\nIntroduction\nDeep contextualised representations of linguistic entities (words and/or sentences) are used in many current state-of-the-art NLP systems. The most well-known examples of ...
[ "2174 million tokens for English and 989 million tokens for Russian" ]
4,026
qasper
020480c5-afea-40e4-bd1c-0023c7aac867
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline systems are proposed?\n\nIntroduction\nThe automatic processing of medical texts and documents plays an increasingly important role in the recent development of the digital health area. To enable dedicated Natural Langua...
[ "Conditional Random Fields, BiLSTM-CRF, Multi-Task Learning, BioBERT" ]
3,587
qasper
02848126-52a3-4e9b-8724-74218ef96c7d
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many users do they look at?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friends are, what t...
[ "22,880 users" ]
5,298
qasper
08e0ab74-383f-4246-be59-91aac8548ae2
[{"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
10c4d32d-31c9-465f-9776-ac2b86c95bc8
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the state of the art?\n\nIntroduction\nInformation extraction tasks have become very important not only in the Web, but also for in-house enterprise settings. One of the crucial steps towards understanding natural language is ...
[ "Babelfy, DBpedia Spotlight, Entityclassifier.eu, FOX, LingPipe MUC-7, NERD-ML, Stanford NER, TagMe 2" ]
4,085
qasper
11685196-1b14-4432-84ea-574735f10217
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does the method achieve sota performance on this dataset?\n\nIntroduction\nThe development of online peer-to-peer markets in the 1990s, galvanized by the launch of sites like eBay, fundamentally shifted the way buyers and sellers coul...
[ "Unanswerable" ]
3,510
qasper
1406516c-538e-4ea5-84b3-370b24de32ab
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What set of approaches to hashtag segmentation are proposed?\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 onl...
[ "Adaptive Multi-task Learning\n, Margin Ranking (MR) Loss\n, Pairwise Neural Ranking Model\n" ]
5,416
qasper
1f180dbf-c096-4665-bfdd-7d9d2ab03815
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which neural embedding model works better?\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 uti...
[ "3C model" ]
5,384
qasper
38cfad22-2240-4a7e-b3d6-45615be7d41a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nMassive Open Online Courses (MOOCs) have strived to bridge the social gap in higher education by bringing quality education from reputed universities to students at large. ...
[ "Unanswerable" ]
4,777
qasper
4a352eb8-b7a9-4367-a50a-f23e29a5c5d7
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How were the cluster extracted? \n\nIntroduction\nMany research attempts have proposed novel features that improve the performance of learning algorithms in particular tasks. Such features are often motivated by domain knowledge or ma...
[ "Word clusters are extracted using k-means on word embeddings" ]
3,559
qasper
55e6c6c0-dc17-468d-8c60-67ae70a45b89
[{"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 ...
[ "Unanswerable" ]
8,580
qasper
5b84b509-c4ab-432e-9d56-b3f7d8ece2ca
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other models do they compare to?\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 lang...
[ "BNA, DocQA, R.M-Reader, R.M-Reader + Verifier, DocQA + ELMo, R.M-Reader+Verifier+ELMo" ]
2,439
qasper
5ea83f87-7124-466c-bfc0-a9926ee7626a
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the source and target domains?\n\nIntroduction\nIn practice, it is often difficult and costly to annotate sufficient training data for diverse application domains on-the-fly. We may have sufficient labeled data in an existing...
[ "we use set 1 of the source domain as the only source with sentiment label information during training, and we evaluate the trained model on set 1 of the target domain, Book (BK), Electronics (E), Beauty (BT), and Music (M)" ]
6,775
qasper
7b82777c-9538-4460-bc48-3fc55d4ec412
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How do profile changes vary for influential leads and their followers over the social movement?\n\nIntroduction\nUser profiles on social media platforms serve as a virtual introduction of the users. People often maintain their online ...
[ "Influential leaders are more likely to change their profile attributes than their followers; the leaders do not change their usernames, while their followers change their usernames a lot; the leaders tend to make new changes related to previous attribute values, while the followers make comparatively less related...
6,816
qasper
7eb18565-4953-4686-bdc6-c712faff3a32
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"which datasets did they experiment with?\n\nIntroduction\nAlthough Neural Machine Translation (NMT) has dominated recent research on translation tasks BIBREF0, BIBREF1, BIBREF2, NMT heavily relies on large-scale parallel data, resulti...
[ "Europarl BIBREF31, MultiUN BIBREF32" ]
5,432
qasper
837b2657-e39d-40c0-a117-ab03266ea07f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their framework automatically optimize for hyperparameters?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaigns ...
[ "Unanswerable" ]
5,748
qasper
89737d23-346e-458f-9ff4-2ad7d950c402
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What sentiment classification dataset 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...
[ "the IMDb movie review dataset BIBREF17" ]
4,697
qasper
9e414ba3-5a29-4049-b691-2091feb5910f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What other evaluation metrics are looked at?\n\nIntroduction\nSarcasm is an intensive, indirect and complex construct that is often intended to express contempt or ridicule . Sarcasm, in speech, is multi-modal, involving tone, body-la...
[ "F-score, Kappa" ]
4,866
qasper
a22a5881-6679-433c-8515-47ebabba8183
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What social media platform did they look at?\n\nIntroduction\nOver the past two decades, the emergence of social media has enabled the proliferation of traceable human behavior. The content posted by users can reflect who their friend...
[ " http://www.blogger.com" ]
5,299
qasper
ac4e24e2-c2e6-43c6-a041-776c80dc492f
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline?\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 Twitter a...
[ "LastStateRNN, AvgRNN, AttentionRNN" ]
3,863
qasper
b0feaff9-dab2-464a-b55c-ae8af740a39e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the best performing model?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most common st...
[ "CNN " ]
3,084
qasper
b150f98f-d674-4f97-a7a7-dd917d2a72eb
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What meaningful information does the GRU model capture, which traditional ML models do not?\n\nIntroduction\nThere have been many advances in machine learning methods which help machines understand human behavior better than ever. One...
[ "information about the context and sequential nature of the text" ]
3,199
qasper
c225b44a-f230-40b2-b480-1b5ffc33d675
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Why are prior knowledge distillation techniques models are ineffective in producing student models with vocabularies different from the original teacher models? \n\nIntroduction\nRecently, contextual-aware language models such as ELM...
[ "distillation techniques cannot utilize these, since they require the student and teacher models to share the same vocabulary and output space. This profoundly limits their potential to further reduce model sizes." ]
4,896
qasper
c4d73026-5dc9-4df0-9ff9-e06cecf5e994
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they inspect their model to see if their model learned to associate image parts with words related to entities?\n\nIntroduction\nSocial media with abundant user-generated posts provide a rich platform for understanding events, opin...
[ "Yes" ]
5,453
qasper
c90a88aa-8aed-4601-9931-d3c8cfb4997e
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which machine learning methods are used in experiments?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively examined from d...
[ "SVMhmm " ]
20,055
qasper
c98dfca2-a7f9-42e2-9972-1a62ca4dcce2
[{"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
ce3c2353-ae1f-4216-8308-b5e6276ea480
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do the errors of the model reflect linguistic similarity between different L1s?\n\nIntroduction\nSeveral learner corpora have been compiled for English, such as the International Corpus of Learner English BIBREF0 . The importance of s...
[ "Unanswerable" ]
2,677
qasper
d6314cfe-776c-4a51-a097-17123b585429
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does BERT reach the best performance among all the algorithms compared?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data...
[ "No" ]
6,156
qasper
d83683e9-d2f9-4a05-a218-f69ea21bd63c
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baseline models?\n\nIntroduction\nIn the kitchen, we increasingly rely on instructions from cooking websites: recipes. A cook with a predilection for Asian cuisine may wish to prepare chicken curry, but may not know all n...
[ "name-based Nearest-Neighbor model (NN), Encoder-Decoder baseline with ingredient attention (Enc-Dec)" ]
3,948
qasper
e124c669-5887-434e-be6a-aaf2e8fc4764
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the dataset collected?\n\nIntroduction\nEnd-to-end speech-to-text translation (ST) has attracted much attention recently BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6 given its simplicity against cascading automatic speech recog...
[ "Contributors record voice clips by reading from a bank of donated sentences." ]
3,596
qasper
e143df15-5838-4392-8ea7-fb139cf025ed
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is MSD prediction?\n\nIntroduction\nThis paper describes our approach and results for Task 2 of the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection BIBREF0 . The task is to generate an inflected word for...
[ "The task of predicting MSD tags: V, PST, V.PCTP, PASS." ]
3,045
qasper
ecafc30a-7537-4772-a1ff-ed5b84b52786
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the three regularization terms?\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 ...
[ "a regularization term associated with neutral features, the maximum entropy of class distribution, KL divergence between reference and predicted class distribution" ]
4,998
qasper
fbeeb88b-e7b5-4302-9533-bf1f7f89e33e
[{"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...
[ "Yes" ]
10,186
qasper
fef5da57-5e94-4618-934a-9965362fa790
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How was the audio data gathered?\n\nINTRODUCTION\nThe idea of language identification is to classify a given audio signal into a particular class using a classification algorithm. Commonly language identification task was done using i...
[ " $\\textbf {All India Radio}$ news channel" ]
3,267
qasper
0023d14f-d7aa-4551-89d5-73349d8290f4
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What kind of sentences were read?\n\nIntroduction\nHow humans process language has become increasingly relevant in natural language processing since physiological data during language understanding is more accessible and recorded with...
[ "sentences that were selected from the Wikipedia corpus provided by culotta2006integrating" ]
4,710
qasper
05117777-3a67-4c29-91a4-60a6274d89f6
[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the approach of previous work?\n\nIntroduction\nAccurate language identification (LID) is the first step in many natural language processing and machine comprehension pipelines. If the language of a piece of text is known then...
[ "'shallow' naive Bayes, SVM, hierarchical stacked classifiers, bidirectional recurrent neural networks" ]
2,610
qasper