{"id":"https://openalex.org/W3007306981","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.468","title":"Training Question Answering Models From Synthetic Data","display_name":"Training Question Answering Models From Synthetic Data","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3007306981","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.468","mag":"3007306981"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.468","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.468.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.emnlp-main.468.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041667198","display_name":"Raul Puri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raul Puri","raw_affiliation_strings":["NVIDIA, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013062640","display_name":"Ryan Spring","orcid":"https://orcid.org/0000-0001-9166-0079"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Spring","raw_affiliation_strings":["Rice University, Houston, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072436307","display_name":"Mohammad Shoeybi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Shoeybi","raw_affiliation_strings":["NVIDIA, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031170568","display_name":"Mostofa Patwary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostofa Patwary","raw_affiliation_strings":["NVIDIA, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041667198"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.9208,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88621759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5811","last_page":"5826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7937872409820557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557147741317749},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6928961277008057},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6923487186431885},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6493545770645142},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.646928071975708},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5764404535293579},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5485315322875977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426748991012573},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47287341952323914},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4446549713611603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43777984380722046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.362712562084198}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7937872409820557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557147741317749},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6928961277008057},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6923487186431885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6493545770645142},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.646928071975708},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5764404535293579},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5485315322875977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426748991012573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47287341952323914},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4446549713611603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43777984380722046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.362712562084198},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2020.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.468","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.468.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.09599","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09599","pdf_url":"https://arxiv.org/pdf/2002.09599","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3007306981","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2002.09599v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.09599","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.09599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.468","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.468.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007306981.pdf","grobid_xml":"https://content.openalex.org/works/W3007306981.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1531374185","https://openalex.org/W1983320747","https://openalex.org/W2136504847","https://openalex.org/W2609826708","https://openalex.org/W2610986956","https://openalex.org/W2612431505","https://openalex.org/W2763421725","https://openalex.org/W2766447205","https://openalex.org/W2796176247","https://openalex.org/W2805206884","https://openalex.org/W2902907165","https://openalex.org/W2911430044","https://openalex.org/W2945260553","https://openalex.org/W2947813521","https://openalex.org/W2949416428","https://openalex.org/W2951365061","https://openalex.org/W2951632090","https://openalex.org/W2951873305","https://openalex.org/W2951936495","https://openalex.org/W2952862139","https://openalex.org/W2953271402","https://openalex.org/W2963341956","https://openalex.org/W2963430447","https://openalex.org/W2964223283","https://openalex.org/W2965373594","https://openalex.org/W2973049837","https://openalex.org/W2973727699","https://openalex.org/W2980282514","https://openalex.org/W2981852735","https://openalex.org/W2984284833","https://openalex.org/W2985963903","https://openalex.org/W2995335514","https://openalex.org/W2996037775","https://openalex.org/W2996428491"],"related_works":["https://openalex.org/W3101007570","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2949849869","https://openalex.org/W2963748441","https://openalex.org/W2962717047","https://openalex.org/W3159460004","https://openalex.org/W2610891036","https://openalex.org/W2745044774","https://openalex.org/W3086409460","https://openalex.org/W3048605183","https://openalex.org/W1565175571","https://openalex.org/W3114047061","https://openalex.org/W1990457736","https://openalex.org/W3101798106","https://openalex.org/W2804340650","https://openalex.org/W2008711674","https://openalex.org/W2935045019","https://openalex.org/W1983212309","https://openalex.org/W2963430447"],"abstract_inverted_index":{"Question":[0],"and":[1,32,50,66,83,103,118,124,140],"answer":[2],"generation":[3],"is":[4],"a":[5,26,106,142],"data":[6,64],"augmentation":[7],"method":[8],"that":[9],"aims":[10,38],"to":[11,39,96,138,150],"improve":[12],"question":[13,72],"answering":[14,73],"(QA)":[15],"models":[16,49],"given":[17],"the":[18,70,88,129],"limited":[19],"amount":[20],"of":[21,46,59,63],"human":[22],"labeled":[23],"data.":[24,155],"However,":[25],"considerable":[27],"gap":[28,42],"remains":[29],"between":[30],"synthetic":[31,81,107,154],"human-generated":[33],"question-answer":[34],"pairs.":[35],"This":[36],"work":[37,152],"narrow":[40],"this":[41],"by":[43,111],"taking":[44],"advantage":[45],"large":[47],"language":[48],"explores":[51],"several":[52],"factors":[53],"such":[54],"as":[55],"model":[56,117],"size,":[57],"quality":[58],"pretrained":[60],"models,":[61],"scale":[62],"synthesized,":[65],"algorithmic":[67],"choices.":[68],"On":[69],"SQUAD1.1":[71,89,130],"task,":[74],"we":[75,100],"achieve":[76,119],"higher":[77],"accuracy":[78],"using":[79,87,153],"solely":[80],"questions":[82,92,102],"answers":[84,104],"than":[85],"when":[86],"training":[90],"set":[91],"alone.":[93],"Removing":[94],"access":[95],"real":[97],"Wikipedia":[98],"data,":[99],"synthesize":[101],"from":[105],"text":[108],"corpus":[109],"generated":[110],"an":[112],"8.3":[113],"billion":[114],"parameter":[115],"GPT-2":[116],"88.4":[120],"Exact":[121],"Match":[122],"(EM)":[123],"93.9":[125],"F1":[126],"score":[127,148],"on":[128,146],"dev":[131],"set.":[132],"We":[133],"further":[134],"apply":[135],"our":[136],"methodology":[137],"SQUAD2.0":[139],"show":[141],"2.8":[143],"absolute":[144],"gain":[145],"EM":[147],"compared":[149],"prior":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}