{"id":"https://openalex.org/W2555428947","doi":"https://doi.org/10.18653/v1/d17-1039","title":"Unsupervised Pretraining for Sequence to Sequence Learning","display_name":"Unsupervised Pretraining for Sequence to Sequence Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2555428947","doi":"https://doi.org/10.18653/v1/d17-1039","mag":"2555428947"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1039","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1039","pdf_url":"https://www.aclweb.org/anthology/D17-1039.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1039.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074823373","display_name":"Prajit Ramachandran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prajit Ramachandran","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102329169","display_name":"Peter Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Liu","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088551093","display_name":"Quoc V. Le","orcid":"https://orcid.org/0000-0002-1087-2844"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quoc Le","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":259,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T11269","display_name":"Algorithms and Data Compression","score":0.9914000034332275,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8616236448287964},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8247399926185608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8131930828094482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7323920726776123},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5941571593284607},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5561211109161377},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5478371381759644},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5078714489936829},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4851396977901459},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48325425386428833},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4743534326553345},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4635068476200104},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4474025368690491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4253774881362915},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4140027165412903},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3915677070617676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.103371262550354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08187833428382874}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8616236448287964},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8247399926185608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131930828094482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7323920726776123},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5941571593284607},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5561211109161377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5478371381759644},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5078714489936829},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4851396977901459},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48325425386428833},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4743534326553345},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4635068476200104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4474025368690491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4253774881362915},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4140027165412903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3915677070617676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.103371262550354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08187833428382874},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1039","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1039","pdf_url":"https://www.aclweb.org/anthology/D17-1039.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1039","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1039","pdf_url":"https://www.aclweb.org/anthology/D17-1039.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2555428947.pdf","grobid_xml":"https://content.openalex.org/works/W2555428947.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W23305027","https://openalex.org/W1522301498","https://openalex.org/W1544827683","https://openalex.org/W1591801644","https://openalex.org/W1753482797","https://openalex.org/W1815076433","https://openalex.org/W1855892484","https://openalex.org/W1915251500","https://openalex.org/W2101105183","https://openalex.org/W2113839990","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2153579005","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2172166122","https://openalex.org/W2250539671","https://openalex.org/W2251994258","https://openalex.org/W2252272516","https://openalex.org/W2259472270","https://openalex.org/W2280798142","https://openalex.org/W2293634267","https://openalex.org/W2293778248","https://openalex.org/W2337676748","https://openalex.org/W2439973210","https://openalex.org/W2508117065","https://openalex.org/W2530876040","https://openalex.org/W2533523411","https://openalex.org/W2561274697","https://openalex.org/W2606347107","https://openalex.org/W2949615363","https://openalex.org/W2952729433","https://openalex.org/W2962784628","https://openalex.org/W2963088995","https://openalex.org/W2963216553","https://openalex.org/W2963271675","https://openalex.org/W2963410018","https://openalex.org/W2963842982","https://openalex.org/W2964007535","https://openalex.org/W2964067969","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W4294170691","https://openalex.org/W4307459710"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W2099607809","https://openalex.org/W2395641992","https://openalex.org/W2807475932","https://openalex.org/W3021126373","https://openalex.org/W2384400852","https://openalex.org/W4280571180","https://openalex.org/W2963259630","https://openalex.org/W2903057408","https://openalex.org/W2070920720"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,29,93,109,140,146],"general":[4],"unsupervised":[5],"learning":[6,143],"method":[7,51,107,138],"to":[8,14,52],"improve":[9],"the":[10,21,24,35,67,78,88,116],"accuracy":[11],"of":[12,23,28,38,80,95,112],"sequence":[13,15],"(seq2seq)":[16],"models.":[17,70,82],"In":[18],"our":[19,137],"method,":[20],"weights":[22,37],"encoder":[25],"and":[26,42,58,61,102,123,134],"decoder":[27],"seq2seq":[30,81],"model":[31],"are":[32],"initialized":[33],"with":[34,45],"pretrained":[36],"two":[39],"language":[40],"models":[41,119],"then":[43],"fine-tuned":[44],"labeled":[46],"data.":[47],"We":[48,83,126],"apply":[49],"this":[50],"challenging":[53],"benchmarks":[54],"in":[55,145],"machine":[56,100,104],"translation":[57,101],"abstractive":[59,132],"summarization":[60,133],"find":[62,135],"that":[63,75,136],"it":[64],"significantly":[65],"improves":[66,77],"subsequent":[68],"supervised":[69,142],"Our":[71,106],"main":[72],"result":[73],"is":[74],"pretraining":[76],"generalization":[79],"achieve":[84],"state-of-theart":[85],"results":[86],"on":[87,120,131],"WMT":[89],"EnglishGerman":[90],"task,":[91],"surpassing":[92],"range":[94],"methods":[96],"using":[97],"both":[98,121],"phrase-based":[99],"neural":[103],"translation.":[105],"achieves":[108],"significant":[110,148],"improvement":[111],"1.3":[113],"BLEU":[114],"from":[115],"previous":[117],"best":[118],"WMT'14":[122],"WMT'15":[124],"EnglishGerman.":[125],"also":[127],"conduct":[128],"human":[129],"evaluations":[130],"outperforms":[139],"purely":[141],"baseline":[144],"statistically":[147],"manner.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":85},{"year":2018,"cited_by_count":42},{"year":2017,"cited_by_count":11}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}