uniq_id stringlengths 36 36 | messages stringlengths 2.65k 180k | answers listlengths 1 1 | num_tokens int64 507 32.7k | task stringclasses 7
values |
|---|---|---|---|---|
07c6bc42-4b8b-4c4b-9a72-dfb6f3cb0e5c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many tags do they look at?\n\nIntroduction\nWhen people shop for books online in e-book stores such as, e.g., the Amazon Kindle store, they enter search terms with the goal to find e-books that meet their preferences. Such e-books... | [
"48,705"
] | 4,426 | qasper |
0a574ef7-e4c4-4d54-868c-2be15fe9a354 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What baseline model is used?\n\nIntroduction\nWikipedia is the largest source of open and collaboratively curated knowledge in the world. Introduced in 2001, it has evolved into a reference work with around 5m pages for the English Wi... | [
"B1. The first baseline uses only the salience-based features by Dunietz and Gillick BIBREF11 ., B2. The second baseline assigns the value relevant to a pair INLINEFORM0 , if and only if INLINEFORM1 appears in the title of INLINEFORM2 .\n\n, S1: Pick the section from template INLINEFORM0 with the highest lexical si... | 10,236 | qasper |
15bfa367-4d96-4763-9312-144fa77baf73 | [{"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... | [
"accuracy, Labeled Attachment Scores (LAS)"
] | 5,300 | qasper |
16948f66-2ed9-466a-a790-852230764b32 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What dataset is used for this work?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassment becomes very common... | [
"Twitter dataset provided by the organizers"
] | 3,866 | qasper |
1b296058-5574-4229-867f-d0657b8b3de9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how is mitigation of gender bias evaluated?\n\nIntroduction\nNatural Language Processing (NLP) models are shown to capture unwanted biases and stereotypes found in the training data which raise concerns about socioeconomic, ethnic and... | [
"Unanswerable"
] | 3,225 | qasper |
2dd01ba5-d58c-4793-99e2-75cc90dae5c2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the performance improvement of the grapheme-level representation model over the character-level model?\n\nIntroduction\nNamed Entity Recognition (NER) is a foremost NLP task to label each atomic elements of a sentence into spe... | [
"On OurNepali test dataset Grapheme-level representation model achieves average 0.16% improvement, on ILPRL test dataset it achieves maximum 1.62% improvement"
] | 4,297 | qasper |
2ee4a564-733e-4351-b652-925e2cb5cdd7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the average length of dialog?\n\nIntroduction\nNowadays, dialog systems are usually designed for a single domain BIBREF0 . They store data in a well-defined format with a fixed number of attributes for entities that the system... | [
"4.49 turns"
] | 3,239 | qasper |
31107072-97ec-49c7-a542-bcd35b668b3d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"where did they obtain the annotated clinical notes from?\n\nIntroduction\nMedical search engines are an essential component for many online medical applications, such as online diagnosis systems and medical document databases. A typic... | [
"clinical notes from the CE task in 2010 i2b2/VA"
] | 4,888 | qasper |
31480059-caa6-402b-b60b-7ace0b12aa09 | [{"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... | [
"update the weights such that the produced sentence embeddings are semantically meaningful and can be compared with cosine-similarity., Classification Objective Function, Regression Objective Function, Triplet Objective Function"
] | 5,617 | qasper |
3a5bf031-2261-4f7d-ba19-ed2260ac2149 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"how many humans evaluated the results?\n\nIntroduction\nMachine translation has made remarkable progress, and studies claiming it to reach a human parity are starting to appear BIBREF0. However, when evaluating translations of the who... | [
"Unanswerable"
] | 5,127 | qasper |
3d940dda-1ccb-4a67-abc1-4c4a7f869a63 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the qualitative experiments performed on benchmark datasets?\n\nIntroduction\nLanguage modelling in its inception had one-hot vector encoding of words. However, it captures only alphabetic ordering but not the word semantic s... | [
"Given a query word and component id, the set of nearest neighbours along with their respective component ids are listed"
] | 3,407 | qasper |
4316b7a5-ad72-47c3-81a6-abed8435af8a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of this dataset?\n\nIntroduction\nSocial media is now becoming an important real-time information source, especially during natural disasters and emergencies. It is now very common for traditional news media to freque... | [
"13,757"
] | 4,646 | qasper |
4643f319-0657-40bd-8920-396987add2ea | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What models are used in the experiment?\n\nIntroduction\nOffensive content has become pervasive in social media and a reason of concern for government organizations, online communities, and social media platforms. One of the most comm... | [
"linear SVM trained on word unigrams, bidirectional Long Short-Term-Memory (BiLSTM), Convolutional Neural Network (CNN) "
] | 3,085 | qasper |
4fb748b6-944f-4df9-8960-465ecea9f5db | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What classifier did they use?\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 elec... | [
"Random Forest"
] | 4,409 | qasper |
682f4765-6690-4bb6-a217-314f46005e3c | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Is the dataset balanced between speakers of different L1s?\n\nIntroduction\nSeveral learner corpora have been compiled for English, such as the International Corpus of Learner English BIBREF0 . The importance of such resources has bee... | [
"No"
] | 2,674 | qasper |
6cef2592-e718-4319-8875-9e5e3f49a648 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the best reported system?\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-language and ... | [
"the MILR classifier"
] | 4,865 | qasper |
71458369-d086-4593-be1c-58167b4d5564 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"In what 8 languages is PolyResponse engine used for restourant search and booking system?\n\nIntroduction and Background\nTask-oriented dialogue systems are primarily designed to search and interact with large databases which contain ... | [
"English (Edinburgh), German (Berlin), Spanish (Madrid), Mandarin (Taipei), Polish (Warsaw), Russian (Moscow), Korean (Seoul), and Serbian (Belgrade)"
] | 3,856 | qasper |
80df7d2d-b450-49ad-945b-52eb8f110892 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the clinical datasets used in the paper?\n\nIntroduction\nDuring the first two decades of the 21st century, the sharing and processing of vast amounts of data has become pervasive. This expansion of data sharing and processin... | [
"MEDDOCAN, NUBes "
] | 6,153 | qasper |
84294437-815c-4971-b135-d959f434bb9d | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of neural model was used?\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 the principle ... | [
"CNN, BERT"
] | 5,279 | qasper |
88e5a353-9cde-441b-9c4b-f47f0ba3e392 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of this dataset?\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 platfor... | [
" 23,700 queries, including 22,500 in-scope queries covering 150 intents, which can be grouped into 10 general domains and 1,200 out-of-scope queries."
] | 3,156 | qasper |
88eb23c0-76d7-45bf-8330-fa2fa414ac69 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many different types of entities exist in 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\", \"OR... | [
"three"
] | 4,290 | qasper |
8aef10ac-f447-470b-b028-dc3e547cf302 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what kinds of male and female words are looked at?\n\nIntroduction\nNatural Language Processing (NLP) models are shown to capture unwanted biases and stereotypes found in the training data which raise concerns about socioeconomic, eth... | [
"gendered word pairs like he and she"
] | 3,228 | qasper |
8e29c10c-aa9d-435c-ac69-ee574819bca7 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What model is used as a baseline? \n\nIntroduction\nReading Comprehension (RC) has become a central task in natural language processing, with great practical value in various industries. In recent years, many large-scale RC datasets ... | [
"pre-trained multi-BERT"
] | 3,415 | qasper |
90423a5c-d050-4dd2-8d63-cc216f1005a1 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What parallel corpus did they use?\n\nIntroduction\nRecently, neural machine translation (NMT) has gained popularity in the field of machine translation. The conventional encoder-decoder NMT proposed by Cho2014 uses two recurrent neur... | [
"Asian Scientific Paper Excerpt Corpus, NTCIR PatentMT Parallel Corpus "
] | 3,066 | qasper |
9407e035-4fcb-4b32-980d-3cf2e4f0d3ce | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which race and gender are given higher sentiment intensity predictions?\n\nIntroduction\n[0]leftmargin=* [0]leftmargin=*\nAutomatic systems have had a significant and beneficial impact on all walks of human life. So much so that it is... | [
"Females are given higher sentiment intensity when predicting anger, joy or valence, but males are given higher sentiment intensity when predicting fear.\nAfrican American names are given higher score on the tasks of anger, fear, and sadness intensity prediction, but European American names are given higher score... | 6,027 | qasper |
a9a173c2-6852-474c-818c-204513a1cf02 | [{"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... | [
"antonym and synonym pairs, collected from WordNet BIBREF9 and Wordnik"
] | 5,402 | qasper |
ad642b28-d849-4bdd-89b8-d9ae55c77223 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does their parallel data differ in terms of style?\n\nIntroduction\nSequence-to-sequence (seq2seq) transformations have recently proven to be a successful framework for several natural language processing tasks, like: machine tran... | [
"Unanswerable"
] | 6,338 | qasper |
b0e965be-bc72-42bb-994d-94c6c362dec8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big is the new Nepali NER 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 oth... | [
"3606 sentences"
] | 4,290 | qasper |
b274e60a-1b49-422e-b7e2-71a92744e7ae | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline model?\n\nIntroduction\nBioASQ is a biomedical document classification, document retrieval, and question answering competition, currently in its seventh year. We provide an overview of our submissions to semantic... | [
"by answering always YES (in batch 2 and 3) "
] | 9,715 | qasper |
b366e2ec-938c-49a4-8c4a-c5e157048f50 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of classifiers 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, such... | [
"Logistic Regression, Multilayer Perceptron"
] | 6,673 | qasper |
b7c16135-ca38-4c65-b2ea-2a990cb71a56 | [{"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... | [
"Our first model is the Concept Raw Context model (CRC) which utilizes concept mentions in a large scale KB to jointly learn embeddings of both words and concepts. Our second model is the Concept-Concept Context model (3C) which learns the embeddings of concepts from their conceptual contexts (i.e., contexts contai... | 5,385 | qasper |
c1ce2b98-2038-4158-a346-6f44cb677452 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English data?\n\nIntroduction\nThe art of argumentation has been studied since the early work of Aristotle, dating back to the 4th century BC BIBREF0 . It has been exhaustively examined from different pe... | [
"Yes"
] | 20,055 | qasper |
d3564912-3e29-4b43-94e8-227411107aef | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the Random Kitchen Sink approach?\n\nIntroduction\nIn this digital era, online discussions and interactions has become a vital part of daily life of which a huge part is covered by social media platforms like twitter, facebook... | [
"Random Kitchen Sink method uses a kernel function to map data vectors to a space where linear separation is possible."
] | 3,368 | qasper |
dc9c6307-cdf5-42ff-95f5-0223a756a495 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How does enforcing agreement between parse trees work across different languages?\n\nIntroduction\nPrepositional Phrase (PP) attachment disambiguation is an important problem in NLP, for it often gives rise to incorrect parse trees . ... | [
"we can expect a dependency edge between i and i' in the English parse tree to correspond to an edge between j and j' in the Hindi parse tree, dual decomposition inference algorithm tries to bring the parse trees in the two languages through its constraints"
] | 2,953 | qasper |
fd5a3998-7246-4d1b-a10b-95fd0702440e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How long of dialog history is captured?\n\nIntroduction\nLanguage model plays an important role in many natural language processing systems, such as in automatic speech recognition BIBREF0 , BIBREF1 and machine translation systems BIB... | [
"two previous turns"
] | 3,782 | qasper |
0207e34f-b433-432b-825c-659cb47232c2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Which natural language(s) are studied in this paper?\n\nIntroduction\nThe challenges of imbalanced classification—in which the proportion of elements in each class for a classification task significantly differ—and of the ability to g... | [
"English"
] | 5,825 | qasper |
0b272118-c08e-4756-9562-3b721197da2a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the languages they use in their experiment?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect and annotate d... | [
"English\nFrench\nSpanish\nGerman\nGreek\nBulgarian\nRussian\nTurkish\nArabic\nVietnamese\nThai\nChinese\nHindi\nSwahili\nUrdu\nFinnish"
] | 5,516 | qasper |
16564619-dbbe-490a-a16f-c7fac13f89b5 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what are the baselines?\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 for opinion increased, commer... | [
"majority baseline corresponds to a model's accuracy if it always predicts the majority class in the dataset, lexicon-based approach"
] | 3,540 | qasper |
2dcd9aac-fed6-4b9d-9079-f37c7812d892 | [{"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, refutation"
] | 20,057 | qasper |
2eefc0ee-444e-4730-b858-cde772401ac9 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What types of online harassment are studied?\n\nIntroduction\nIn the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. In fact, online harassment becomes ve... | [
"indirect harassment, sexual and physical harassment"
] | 3,866 | qasper |
36a1034f-f33d-4573-9573-1a4b6714a441 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the size of the StackExchange dataset?\n\nIntroduction\nKeyphrase generation is the task of automatically predicting keyphrases given a source text. Desired keyphrases are often multi-word units that summarize the high-level m... | [
"Unanswerable"
] | 6,248 | qasper |
389641dd-1dc1-498f-9016-f65f3851bdee | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What experiments are conducted?\n\nIntroduction\nThe irony is a kind of figurative language, which is widely used on social media BIBREF0 . The irony is defined as a clash between the intended meaning of a sentence and its literal mea... | [
"Irony Classifier, Sentiment Classifier for Irony, Sentiment Classifier for Non-irony, transformation from ironic sentences to non-ironic sentences"
] | 6,077 | qasper |
3df3bf85-8f2d-41b7-a75a-35aa28edbe50 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What type of evaluation is proposed for this task?\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 N... | [
"Answer with content missing: (Evaluation Metrics section) Precision, Recall, F1-scores, Strict match, METEOR, ROUGE-2"
] | 5,676 | qasper |
4467791f-4329-4f60-9abc-81e63e000ebd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Does their framework always generate purely attention-based models?\n\nIntroduction\nNeural Machine Translation (NMT) has shown its effectiveness in translation tasks when NMT systems perform best in recent machine translation campaig... | [
"Yes"
] | 5,749 | qasper |
4589f21e-c227-4e15-9398-73111c68509a | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What background knowledge do they leverage?\n\nIntroduction\nWe posses a wealth of prior knowledge about many natural language processing tasks. For example, in text categorization, we know that words such as NBA, player, and basketba... | [
"labeled features"
] | 4,998 | qasper |
4b3daa46-6e6b-4681-b353-6639be9a1d08 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What crowdsourcing platform is used?\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 with other ... | [
"Unanswerable"
] | 8,637 | qasper |
5527afbb-c4c3-425d-88ba-6c8b3a042fdc | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they only use adjacent entity mentions or use more than that in some cases (next to adjacent)?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International License. License details: http://creativec... | [
"NCEL considers only adjacent mentions."
] | 5,756 | qasper |
57bb9aad-271a-46ae-aa7c-fec3964577aa | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are examples of these artificats?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect and annotate data in multipl... | [
"the degree of lexical overlap between them, presence of negation words"
] | 5,515 | qasper |
596df02e-4729-4644-8875-cec11852b546 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what is the size of the augmented dataset?\n\nIntroduction\nAlzheimer’s disease (AD) is a neurodegenerative disease affecting over 40 million people worldwide with high costs of acute and long-term care BIBREF0 . Recruitment of partic... | [
"Unanswerable"
] | 3,523 | qasper |
69b711d8-4d0e-4765-b7db-8672c993c90e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the distinctive characteristics of how Arabic speakers use offensive language?\n\nIntroduction\nDisclaimer: Due to the nature of the paper, some examples contain highly offensive language and hate speech. They don't reflect t... | [
"Frequent use of direct animal name calling, using simile and metaphors, through indirect speech like sarcasm, wishing evil to others, name alteration, societal stratification, immoral behavior and sexually related uses."
] | 7,109 | qasper |
6c4ec115-287b-4c1f-ac1e-b19c1d85d32f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the baselines?\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 widely used in ... | [
"SVM with unigram, bigram, and trigram features, SVM with average word embedding, SVM with average transformed word embeddings, CNN, ecurrent Convolutional Neural Networks, SVM and deep learning models with comment information"
] | 5,895 | qasper |
6e4ff4a1-28c0-491e-a4ff-7dd76e0dbe2f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages are the model transferred to?\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 pr... | [
"French (fr), Russian (ru), Arabic (ar), Chinese (zh), Hindi (hi), and Vietnamese (vi)"
] | 5,301 | qasper |
6f077632-bd54-4c48-9357-44604a7e3b7e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they recommend translating the premise and hypothesis together?\n\nIntroduction\nWhile most NLP resources are English-specific, there have been several recent efforts to build multilingual benchmarks. One possibility is to collect ... | [
"No"
] | 5,516 | qasper |
71ef59dd-00c7-4ec3-880f-243ab2190a45 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What are the three layers of the annotation scheme?\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 t... | [
"Level A: Offensive language Detection\n, Level B: Categorization of Offensive Language\n, Level C: Offensive Language Target Identification\n"
] | 3,087 | qasper |
83599348-8d2f-47b0-bb14-c147bce15e61 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much improvement is gained from Adversarial Reward Augmented Maximum Likelihood (ARAML)?\n\nIntroduction\nNatural text generation, as a key task in NLP, has been advanced substantially thanks to the flourish of neural models BIBRE... | [
"Compared to the baselines, ARAML does not do better in terms of perplexity on COCO and EMNLP 2017 WMT datasets, but it does by up to 0.27 Self-BLEU points on COCO and 0.35 Self-BLEU on EMNLP 2017 WMT. In terms of Grammaticality and Relevance, it scores better than the baselines on up to 75.5% and 73% of the cases ... | 5,230 | qasper |
9419ae81-112f-4c77-92bd-c9096123f3eb | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What evaluation metrics did look at?\n\nIntroduction\nBack to 42 BC, the philosopher Cicero has raised the issue that although there were many Oratory classes, there were none for Conversational skills BIBREF0 . He highlighted how imp... | [
"Response time, resource consumption (memory, CPU, network bandwidth), precision, recall, F1, accuracy."
] | 17,790 | qasper |
9587d12e-892a-4470-bd6a-99fe11760b4b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How many categories do authors define for speaker role?\n\nIntroduction\nIn recent years, gender has become a hot topic within the political, societal and research spheres. Numerous studies have been conducted in order to evaluate the... | [
" two salient roles called Anchors and Punctual speakers"
] | 5,377 | qasper |
9e009302-87e2-4384-86f2-c2b86fdf0a3f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What architecture does the decoder have?\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 i... | [
"LSTM"
] | 3,047 | qasper |
a22521c1-6b97-459e-9d71-b878233daeec | [{"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 |
b1a27e9c-8509-44a0-bc89-0c2584919261 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"what keyphrase extraction models were reassessed?\n\nIntroduction\nThis work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by/4.0/\nRecent years have s... | [
"Answer with content missing: (LVL1, LVL2, LVL3) \n- Stanford CoreNLP\n- Optical Character Recognition (OCR) system, ParsCIT \n- further abridge the input text from level 2 preprocessed documents to the following: title, headers, abstract, introduction, related work, background and conclusion."
] | 2,276 | qasper |
b3f0890b-00d8-4302-acb4-8e5ecd61a37e | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Are the annotations automatic or manually created?\n\nIntroduction\nSeveral learner corpora have been compiled for English, such as the International Corpus of Learner English BIBREF0 . The importance of such resources has been increa... | [
"We performed the annotation with freely available tools for the Portuguese language."
] | 2,670 | qasper |
c62f9772-b6a1-442e-b5d4-3d324bf81cfd | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is the baseline?\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. There... | [
"Bam et al. SVM, Ma and Hovy w/glove, Lample et al. w/fastText, Lample et al. w/word2vec"
] | 4,284 | qasper |
cd8897eb-075b-4896-a980-5e09bfc51dc3 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Do they report results only on English dataset?\n\nData\nWe build and test our MMT models on the Multi30K dataset BIBREF21 . Each image in Multi30K contains one English (EN) description taken from Flickr30K BIBREF22 and human translat... | [
"No"
] | 2,505 | qasper |
d441b910-65d2-4414-8509-22fdf31ca153 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What predictive model do they build?\n\nIntroduction\n“I'm supposed to trust the opinion of a MS minion? The people that produced Windows ME, Vista and 8? They don't even understand people, yet they think they can predict the behavior... | [
"logistic regression models"
] | 5,755 | qasper |
daae633c-a8a6-4f41-bad6-b7ca80a3c00b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What was the baseline for this task?\n\nIntroduction\nPropaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. In the Internet era, thanks to the mechanism of sharing in social networks, propaga... | [
"SLC task is a very simple logistic regression classifier, FLC task generates spans and selects one of the 18 techniques randomly"
] | 4,230 | qasper |
db62d517-9b77-464d-a059-8f000ef45b7f | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How big are improvements of small-scale unbalanced datasets when sentence representation is enhanced with topic information?\n\nIntroduction\nMedical text mining is an exciting area and is becoming attractive to natural language proce... | [
"7.36% on accuracy and 9.69% on F1 score"
] | 4,075 | qasper |
e1194cb1-5e76-4eb5-9687-746d2f810b5b | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"How much does this model improve state-of-the-art?\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 units a... | [
"the basic model yields good performance for recognizing explicit discourse relations as well, which is comparable with previous best result (92.05% macro F1-score and 93.09% accuracy as reported in BIBREF11 )., full paragraph-level neural network model achieves the best macro-average F1-score of 48.82% in predicti... | 5,574 | qasper |
e8f93413-75ba-4dd2-9742-4a9cabfb8da8 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What metrics are used to establish that this makes chatbots more knowledgeable and better at learning and conversation? \n\nIntroduction\nChatbots such as dialog and question-answering systems have a long history in AI and natural lan... | [
"strategy formulation ability, we introduce a measure called Coverage( INLINEFORM0 ), To evaluate the predictive performance, we use Avg. MCC and avg. +ve F1 score"
] | 8,591 | qasper |
ef0e5650-039d-45d4-b847-c0c696d44cc2 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What languages are evaluated?\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 wo... | [
"German, English, Spanish, Finnish, French, Russian, Swedish."
] | 3,045 | qasper |
f09a0d1c-0e4e-471a-b8ad-e92877552d7e | [{"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... | [
"5"
] | 2,985 | qasper |
f11180f9-c78d-4e98-bb18-7873838c5c36 | [{"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), METEOR (MET), ROUGE-L (R-L)"
] | 5,603 | qasper |
f6fa9445-2582-46c2-a837-3e23b3379227 | [{"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... | [
" pre-trained GloVe word vectors "
] | 3,079 | qasper |
ff2ffb97-7df1-4078-a1c3-61dfd5e48474 | [{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What features are extracted?\n\nIntroduction\nSocial media platforms have made the spreading of fake news easier, faster as well as able to reach a wider audience. Social media offer another feature which is the anonymity for the auth... | [
"Sentiment, Morality, Style, Words embeddings"
] | 2,880 | qasper |
0c55352b-7614-43c6-a9de-f2bc36ea18a6 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThe program activities of most federal agencies are generally funded on an annual basis through the enactment of 12 regular app... | [
"The program activities of most federal agencies are generally funded on an annual basis through the enactment of regular appropriations acts. When those annual appropriations acts are not enacted by the beginning of the fiscal year (i.e., by October 1), one or more continuing appropriations acts (commonly known as... | 8,044 | gov_report |
183ff296-257e-47d5-9f11-55bdc43a82c6 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nThe Defense Base Closure and Realignment Act of 1990, as amended, has governed the BRAC process since 1990. The law established ... | [
"Why GAO Did This Study\n\nDOD has used the Base Realignment and Closure (BRAC) process primarily to reduce excess infrastructure capacity, transform the force, and produce cost savings. DOD completed hundreds of base closures and realignments in previous BRAC rounds and intends to work with Congress to address rem... | 9,847 | gov_report |
4cd9ee7a-ccba-491b-8897-357535046378 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThe Railroad Retirement Board (RRB), an independent federal agency, administers retirement, survivor, disability, unemployment,... | [
"The Railroad Retirement Board (RRB), an independent federal agency, administers retirement, survivor, disability, unemployment, and sickness insurance for railroad workers and their families. During FY2017, the RRB paid nearly $12.5 billion in retirement, disability, and survivor benefits to approximately 548,000 ... | 5,044 | gov_report |
6227866a-d8d1-4137-ad95-f5b27c6cb1d1 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nThe federal government receives funds from numerous sources in addition to tax revenues, including collections of user fees, fin... | [
"Why GAO Did This Study\n\nCongress has authorized federal agencies to collect hundreds of billions of dollars annually in fees, fines, and penalties. These collections can fund a variety of programs, including programs related to national security, and the protection of natural resources. Data on collections are i... | 11,991 | gov_report |
ac619f46-d4ef-4bf3-b7bf-b0b2b1797a39 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tOverview\n\nThe low-income housing tax credit (LIHTC) was created by the Tax Reform Act of 1986 ( P.L. 99-514 ) to provide an incentive for the... | [
"The low-income housing tax credit (LIHTC) program is one of the federal government's primary policy tools for encouraging the development and rehabilitation of affordable rental housing. These nonrefundable federal housing tax credits are awarded to developers of qualified rental projects via a competitive applica... | 2,925 | gov_report |
c755ad10-824d-403b-bdf8-1720d7f8eb40 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tCMS Delegates Monitoring of Beneficiaries who Receive Opioid Prescriptions to Plan Sponsors, but Does Not Have Sufficient Information on Those ... | [
"Why GAO Did This Study\n\nMisuse of prescription opioids can lead to overdose and death. In 2016, over 14 million Medicare Part D beneficiaries received opioid prescriptions, and spending for opioids was almost $4.1 billion. GAO and others have reported on inappropriate activities and risks associated with these p... | 3,297 | gov_report |
cac2e4e5-a1c9-41d7-92ac-bb24a1e2d04f | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\n\t\tRegulatory Flexibility Act\n\nRFA requires that federal agencies, including financial regulators, engaged in substantive rul... | [
"Why GAO Did This Study\n\nFederal financial regulators must comply with various rulemaking and review requirements, including those in RFA and EGRPRA. These statutes require analyses relating to regulatory burden, small entities, or both. RFA requires analyses of a rule's impact on small entities and alternatives ... | 6,142 | gov_report |
29bd8396-21ad-45a4-a6c7-2dea35b95680 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nRPS are long-lived sources of spacecraft electrical power and heating that are rugged, compact, highly reliable, and relatively ... | [
"Why GAO Did This Study\n\nThis testimony summarizes the information contained in GAO's September 2017 report, entitled Space Exploration: DOE Could Improve Planning and Communication Related to Plutonium-238 and Radioisotope Power Systems Production Challenges ( GAO-17-673 ).\n\nWhat GAO Found\n\nThe National Aero... | 3,630 | gov_report |
3ead3506-e65b-4545-aa9f-87c6cd063ee5 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nThis section includes information about seismic surveys, oil and gas activities in the four OCS regions, and the potential effec... | [
"Why GAO Did This Study\n\nOffshore seismic surveys provide federal agencies and other entities with a wide range of data, from research on fault zones to geology that may indicate the presence of oil and gas. Companies seeking to conduct such surveys to find oil and gas resources in the OCS must obtain a permit fr... | 11,511 | gov_report |
40cd124f-a20c-4d7b-af8c-8aa97ced47c9 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThe U.S. energy pipeline network is integral to the nation's energy supply and provides vital links to other critical infrastru... | [
"The U.S. energy pipeline network is composed of approximately 3 million miles of pipeline transporting natural gas, oil, and other hazardous liquids. Recent incidents in California, Pennsylvania, Massachusetts, and other states have drawn criticism from stakeholders and have raised concerns in Congress about pipel... | 12,484 | gov_report |
45a9f436-3b6f-4d39-bf48-ad27221e4868 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nRadiological material is used throughout the world for medical and industrial purposes. Possession of this material within the U... | [
"Why GAO Did This Study\n\nThousands of shipments containing radiological material enter the United States each year through airports across the country. Radiological material is used in various medical and industrial applications, and possession requires a license from the Nuclear Regulatory Commission (NRC) or on... | 6,103 | gov_report |
45b07b40-a304-4aa5-9b84-9c2be772eccc | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nSince the onset of the nation's civil war and ensuing military coup d'état in 1962, Burma's military, or Tatmadaw, and its asso... | [
"At least 17 different reports by United Nations (U.N.) entities and independent human rights organizations have been released containing allegations that certain Burmese security force officers and units committed serious human rights violations dating back to 2011. These reports name nearly 40 individuals and ove... | 7,735 | gov_report |
707bbcc8-08ce-4b0a-9353-acde2792499b | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThe National Flood Insurance Program (NFIP) was created by the National Flood Insurance Act of 1968 (NFIA). The NFIP received a... | [
"The National Flood Insurance Program (NFIP) was established by the National Flood Insurance Act of 1968 (NFIA, 42 U.S.C. §4001 et seq.), and was most recently reauthorized to May 31, 2019, through a series of short-term reauthorizations. The general purpose of the NFIP is both to offer primary flood insurance to p... | 11,617 | gov_report |
7c30e817-fa3d-40d5-bf46-a41ae64519ea | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nThis section describes (1) NNSA’s weapons design and production sites; (2) the framework for managing LEPs, known as the Phase 6... | [
"Why GAO Did This Study\n\nThe Department of Defense and NNSA have sought for nearly a decade to replace the capabilities of the aging W78 nuclear warhead used by the U.S. Air Force. NNSA undertakes LEPs to refurbish or replace the capabilities of nuclear weapons components. In fiscal year 2014, NNSA was directed t... | 6,795 | gov_report |
bcfe21ef-6991-4e68-8a0a-303eeb973d25 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tOverview\n\nIn March 2015, Saudi Arabia established a coalition of nations (hereinafter referred to as the Saudi-led coalition or the coalition... | [
"This product provides an overview of the role Congress has played in shaping U.S. policy toward the conflict in Yemen. Summary tables provide information on legislative proposals considered in the 115th and 116th Congresses. Various legislative proposals have reflected a range of congressional perspectives and pri... | 6,700 | gov_report |
c74bd54e-5fb9-4744-af31-a1b986dd9f6f | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nPart of the Mariana Islands Archipelago, the CNMI is a chain of 14 islands in the western Pacific Ocean, just north of Guam and ... | [
"Why GAO Did This Study\n\nPub. L. No. 110-229, enacted in 2008, amended the U.S.-CNMI covenant to apply federal immigration law to the CNMI after a transition period. The law required the Department of Homeland Security (DHS) to establish a temporary work permit program for foreign workers. DHS is required to decr... | 2,984 | gov_report |
ea2847bd-8ef7-4203-ad72-162f4f32e042 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nMental health disorders affect millions of adults and children in the United States and can range in severity. In 2016, an estim... | [
"Why GAO Did This Study\n\nPAIMI grant awards, established by Congress in 1986 and totaling $36 million in 2016, are administered by SAMHSA to support state protection and advocacy programs. PAIMI programs protect and advocate for the rights of individuals with significant mental illness by investigating reports of... | 6,472 | gov_report |
fd868260-0717-45ad-9500-4ecb6237ef74 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\n\t\tSpending Authority and Permanent Appropriations\n\n“Backdoor Authority” or “Backdoor Spending” These are similar but not id... | [
"Why GAO Did This Study\n\nCongress can provide budget authority to federal agencies and programs through the annual appropriations process. It can also provide budget authority through laws other than annual appropriations acts, or through permanent appropriations that permit the agency to obligate budget authorit... | 11,950 | gov_report |
19bfdf8c-6019-4d9f-aac3-88dc44e5d97e | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nRRB administers retirement, survivor, disability, unemployment, and sickness benefits for railroad workers and their families un... | [
"Why GAO Did This Study\n\nRRB is an independent agency that administers disability benefits for railroad workers. In fiscal year 2016, about 31,000 railroad workers with disabilities received $1.1 billion in disability benefits. RRB is generally required to periodically assess beneficiaries' medical condition or e... | 7,900 | gov_report |
242d6fac-158b-4781-ac08-9fc029433edf | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\n\t\tU.S. Law Requires State to Convene an ARB after Certain Types of Incidents\n\nFederal law generally requires the Secretary of... | [
"Why GAO Did This Study\n\nU.S. diplomats and their families in Havana, Cuba, were affected by incidents that were associated with injuries, including hearing loss and brain damage. Over State has reported that over 20 U.S. diplomats and family members in Havana have suffered from medical conditions believed to be ... | 4,510 | gov_report |
3e24cff1-b8e1-48b6-80ae-b93ab84844c6 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\n\t\tFEMA’s Public Assistance Grant Program\n\nMajor disaster declarations can trigger a variety of federal response and recovery... | [
"Why GAO Did This Study\n\nFEMA, an agency of the Department of Homeland Security (DHS), has obligated more than $36 billion in PA grants to state, local, and tribal governments to help communities recover and rebuild after major disasters since 2009. Further, costs are rising with disasters, such as Hurricanes Har... | 16,138 | gov_report |
9f82b885-de44-47dc-a88e-c968b9124c44 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThis report provides background information and analysis on the following topics:\nVarious aspects of U.S.-Turkey relations, in... | [
"The United States and Turkey have been NATO allies since 1952 and share some vital interests, but harmonizing their priorities can be difficult. These priorities sometimes diverge irrespective of who leads the two countries, based on contrasting geography, threat perceptions, and regional roles.\nTurkey's core sec... | 5,888 | gov_report |
b0f69943-e8c5-4e3b-89b5-3cf95161a667 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tIntroduction\n\nThis report provides background information and issues for Congress on the Navy's Littoral Combat Ship (LCS) program. A total o... | [
"The Navy began procuring a small surface combatant called the Littoral Combat Ship (LCS) in FY2005, and a total of 35 LCSs have been procured through FY2019, including three in FY2019. The total of 35 LCSs is three more than the 32 the Navy says are required under its 355-ship force-level goal. The Navy wants FY20... | 5,891 | gov_report |
c45ed318-2d42-4ef9-b9f7-226beabc4b88 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nThe Coast Guard is required to develop, establish, maintain, and operate rescue facilities for the promotion of safety and may a... | [
"Why GAO Did This Study\n\nThe Coast Guard, within the Department of Homeland Security (DHS), is charged with preventing loss of life, injury, and property damage in the maritime environment through its SAR mission. It maintains over 200 stations with various assets, such as boats and helicopters (depending on the ... | 11,020 | gov_report |
c5329dd4-bc53-41b7-8d68-c8f4558d8c12 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tFCC’s Data Overstate Broadband Access on Tribal Lands\n\nIn our September 2018 report on broadband access on tribal lands, we found that FCC c... | [
"Why GAO Did This Study\n\nThis testimony summarizes the information contained in two GAO reports: Broadband Internet: FCC’s Data Overstate Access on Tribal Lands , ( GAO-18-630 ) and Tribal Broadband: Few Partnerships Exist and the Rural Utilities Service Needs to Identify and Address Any Funding Barriers Tribes F... | 2,972 | gov_report |
d1da9658-c284-4e15-b8d6-f6a4f041a372 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\n\t\tMedicaid Section 1115 Demonstrations\n\nNearly three-quarters of states (37 as of November 2016) have CMS- approved Medicaid ... | [
"Why GAO Did This Study\n\nDemonstrations—which represented roughly a third of the more than $300 billion in federal Medicaid spending in 2015—are a powerful tool to test new approaches to providing coverage and delivering Medicaid services that could reduce costs and improve beneficiaries' outcomes. Evaluations ar... | 8,701 | gov_report |
d369d346-261a-47e9-a45f-41192509c865 | [{"role":"system","content":"You are a helpful assistant that summarizes government reports."},{"role":"user","content":"Please provide a summary for the following report:\n\n\tBackground\n\nFederal acquisition regulations require certain contractors who do business with the government to maintain acceptable business ... | [
"Why GAO Did This Study\n\nContractor business systems produce critical data that contracting officers use to help negotiate and manage defense contracts. These systems and their related internal controls act as important safeguards against fraud, waste, and abuse of federal funding. Federal and defense acquisition... | 9,598 | gov_report |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.