{"id":"https://openalex.org/W2953039584","doi":"https://doi.org/10.18653/v1/p19-1608","title":"Large-Scale Transfer Learning for Natural Language Generation","display_name":"Large-Scale Transfer Learning for Natural Language Generation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2953039584","doi":"https://doi.org/10.18653/v1/p19-1608","mag":"2953039584"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1608","pdf_url":"https://www.aclweb.org/anthology/P19-1608.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1608.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036396511","display_name":"Sergey Golovanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sergey Golovanov","raw_affiliation_strings":["Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia"],"affiliations":[{"raw_affiliation_string":"Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003461656","display_name":"Rauf Kurbanov","orcid":"https://orcid.org/0000-0002-5153-0373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rauf Kurbanov","raw_affiliation_strings":["Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia"],"affiliations":[{"raw_affiliation_string":"Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045523675","display_name":"Sergey Nikolenko","orcid":"https://orcid.org/0000-0001-7787-2251"},"institutions":[{"id":"https://openalex.org/I2801160905","display_name":"Steklov Mathematical Institute","ror":"https://ror.org/03zeg8w71","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2801160905","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Nikolenko","raw_affiliation_strings":["Steklov Mathematical Institute at St. Petersburg, nab. r. Fontanki 27, St. Petersburg 191023, Russia"],"affiliations":[{"raw_affiliation_string":"Steklov Mathematical Institute at St. Petersburg, nab. r. Fontanki 27, St. Petersburg 191023, Russia","institution_ids":["https://openalex.org/I2801160905"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004421303","display_name":"Kyryl Truskovskyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyryl Truskovskyi","raw_affiliation_strings":["Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia"],"affiliations":[{"raw_affiliation_string":"Neuromation OU, Liivalaia tn 45, 10145 Tallinn, Estonia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075548089","display_name":"Alexander Tselousov","orcid":null},"institutions":[{"id":"https://openalex.org/I2801160905","display_name":"Steklov Mathematical Institute","ror":"https://ror.org/03zeg8w71","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2801160905","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexander Tselousov","raw_affiliation_strings":["Steklov Mathematical Institute at St. Petersburg, nab. r. Fontanki 27, St. Petersburg 191023, Russia"],"affiliations":[{"raw_affiliation_string":"Steklov Mathematical Institute at St. Petersburg, nab. r. Fontanki 27, St. Petersburg 191023, Russia","institution_ids":["https://openalex.org/I2801160905"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107899645","display_name":"Thomas Wolf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Wolf","raw_affiliation_strings":["Huggingface Inc., 81 Prospect St. Brooklyn, New York 11201, USA"],"affiliations":[{"raw_affiliation_string":"Huggingface Inc., 81 Prospect St. Brooklyn, New York 11201, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036396511"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3179,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98277079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6053","last_page":"6058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519388437271118},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6847008466720581},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6086033582687378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591638445854187},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5592716932296753},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5551561713218689},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5103487372398376},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4616021513938904},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.460550457239151},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44238147139549255},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43968039751052856},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43859896063804626},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43072110414505005},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42264753580093384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07560363411903381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519388437271118},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6847008466720581},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6086033582687378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591638445854187},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5592716932296753},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5551561713218689},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5103487372398376},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4616021513938904},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.460550457239151},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44238147139549255},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43968039751052856},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43859896063804626},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43072110414505005},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42264753580093384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07560363411903381},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1608","pdf_url":"https://www.aclweb.org/anthology/P19-1608.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1608","pdf_url":"https://www.aclweb.org/anthology/P19-1608.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953039584.pdf","grobid_xml":"https://content.openalex.org/works/W2953039584.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2259472270","https://openalex.org/W2550821151","https://openalex.org/W2555428947","https://openalex.org/W2784121710","https://openalex.org/W2891068404","https://openalex.org/W2896457183","https://openalex.org/W2913443447","https://openalex.org/W2914120296","https://openalex.org/W2914204778","https://openalex.org/W2922349260","https://openalex.org/W2923014074","https://openalex.org/W2950726992","https://openalex.org/W2952729433","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2963825865","https://openalex.org/W2964213727","https://openalex.org/W4288624561","https://openalex.org/W4289549143","https://openalex.org/W4294170691","https://openalex.org/W4302400662","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3156493709","https://openalex.org/W3034800807","https://openalex.org/W4287758468","https://openalex.org/W4230258867","https://openalex.org/W3035130722","https://openalex.org/W3034878914","https://openalex.org/W4310731959","https://openalex.org/W3019688513","https://openalex.org/W2386843486","https://openalex.org/W3092480528"],"abstract_inverted_index":{"Large-scale":[0],"pretrained":[1,64],"language":[2,11,33],"models":[3,65],"define":[4],"state":[5,67],"of":[6,19,38,68],"the":[7,69],"art":[8,70],"in":[9,45],"natural":[10,32],"processing,":[12],"achieving":[13],"outstanding":[14],"performance":[15],"on":[16,47],"a":[17,36,51],"variety":[18],"tasks.":[20],"We":[21,43],"study":[22],"how":[23],"these":[24],"architectures":[25,61],"can":[26],"be":[27],"applied":[28],"and":[29,40,58],"adapted":[30],"for":[31,62],"generation,":[34],"comparing":[35,59],"number":[37],"architectural":[39],"training":[41],"schemes.":[42],"focus":[44],"particular":[46],"open-domain":[48],"dialog":[49],"as":[50],"typical":[52],"high":[53],"entropy":[54],"generation":[55],"task,":[56],"presenting":[57],"different":[60],"adapting":[63],"with":[66],"results.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}