{"id":"https://openalex.org/W2963736842","doi":"https://doi.org/10.18653/v1/d16-1139","title":"Sequence-Level Knowledge Distillation","display_name":"Sequence-Level Knowledge Distillation","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963736842","doi":"https://doi.org/10.18653/v1/d16-1139","mag":"2963736842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1139","pdf_url":"https://www.aclweb.org/anthology/D16-1139.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 2016 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/D16-1139.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693798","display_name":"Yoon Kim","orcid":"https://orcid.org/0000-0002-4837-8411"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoon Kim","raw_affiliation_strings":["School of Engineering and Applied Sciences Harvard University Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences Harvard University Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062546146","display_name":"Alexander M. Rush","orcid":"https://orcid.org/0000-0002-9900-1606"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander M. Rush","raw_affiliation_strings":["School of Engineering and Applied Sciences Harvard University Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences Harvard University Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":785,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1317","last_page":"1327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/distillation","display_name":"Distillation","score":0.8510546684265137},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7509986758232117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475293874740601},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.6517826318740845},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6246184706687927},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6012142896652222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49762752652168274},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45814651250839233},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4565261900424957},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4463655650615692},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4213111698627472},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4158395528793335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24683552980422974},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.1662292182445526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15830263495445251}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8510546684265137},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7509986758232117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475293874740601},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.6517826318740845},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6246184706687927},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6012142896652222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49762752652168274},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45814651250839233},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4565261900424957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4463655650615692},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4213111698627472},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4158395528793335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24683552980422974},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.1662292182445526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15830263495445251},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d16-1139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1139","pdf_url":"https://www.aclweb.org/anthology/D16-1139.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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1139","pdf_url":"https://www.aclweb.org/anthology/D16-1139.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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963736842.pdf","grobid_xml":"https://content.openalex.org/works/W2963736842.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W992687842","https://openalex.org/W1514535095","https://openalex.org/W1591706642","https://openalex.org/W1690739335","https://openalex.org/W1737559646","https://openalex.org/W1753482797","https://openalex.org/W1821462560","https://openalex.org/W1843891098","https://openalex.org/W1855892484","https://openalex.org/W1869752048","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1928693685","https://openalex.org/W1931877416","https://openalex.org/W1938755728","https://openalex.org/W1996901117","https://openalex.org/W2084910356","https://openalex.org/W2101105183","https://openalex.org/W2114766824","https://openalex.org/W2116435618","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2134797427","https://openalex.org/W2136933783","https://openalex.org/W2143177362","https://openalex.org/W2143564602","https://openalex.org/W2146574666","https://openalex.org/W2157331557","https://openalex.org/W2158349948","https://openalex.org/W2158614781","https://openalex.org/W2172166488","https://openalex.org/W2259472270","https://openalex.org/W2294370754","https://openalex.org/W2312434537","https://openalex.org/W2319920447","https://openalex.org/W2402040300","https://openalex.org/W2949600092","https://openalex.org/W2950178297","https://openalex.org/W2951559648","https://openalex.org/W2952432176","https://openalex.org/W2952453038","https://openalex.org/W2952533036","https://openalex.org/W2952822287","https://openalex.org/W2952899695","https://openalex.org/W2962732637","https://openalex.org/W2962883855","https://openalex.org/W2962957031","https://openalex.org/W2962965405","https://openalex.org/W2963069010","https://openalex.org/W2963208801","https://openalex.org/W2963213121","https://openalex.org/W2963463964","https://openalex.org/W2963927463","https://openalex.org/W2963991316","https://openalex.org/W2963991999","https://openalex.org/W2964118293","https://openalex.org/W2964200805","https://openalex.org/W2964217848","https://openalex.org/W2964299589","https://openalex.org/W4285719527","https://openalex.org/W4293871399","https://openalex.org/W4297813615"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W4386269615","https://openalex.org/W3204412157","https://openalex.org/W2463507112"],"abstract_inverted_index":{"Neural":[0],"machine":[1],"translation":[2,10],"(NMT)":[3],"offers":[4],"a":[5,110,134,148],"novel":[6,58],"alternative":[7],"formulation":[8],"of":[9,61,129,150],"that":[11,41,64,137],"is":[12,105],"potentially":[13],"simpler":[14],"than":[15,95,109,142],"statistical":[16],"approaches.":[17],"However":[18],"to":[19,26,46,72],"reach":[20],"competitive":[21],"performance,":[22,67],"NMT":[23],"models":[24],"need":[25,75],"be":[27,50],"exceedingly":[28],"large.":[29],"In":[30],"this":[31],"paper":[32],"we":[33],"consider":[34],"applying":[35],"knowledge":[36,43,62,115,130],"distillation":[37,44,63,131],"approaches":[38],"We":[39],"demonstrate":[40],"standard":[42],"applied":[45,81],"word-level":[47],"prediction":[48],"can":[49],"effective":[51],"for":[52,76],"NMT,":[53],"and":[54,68],"also":[55,106],"introduce":[56],"two":[57],"sequence-level":[59],"versions":[60],"further":[65],"improve":[66],"somewhat":[69],"surprisingly,":[70],"seem":[71],"eliminate":[73],"the":[74,83,143],"beam":[77],"search":[78],"(even":[79],"when":[80],"on":[82,127],"original":[84,144],"teacher":[85,98,145],"model).":[86],"Our":[87],"best":[88],"student":[89,135],"model":[90,112,136],"runs":[91],"10":[92],"times":[93],"faster":[94],"its":[96],"state-of-the-art":[97],"with":[99,120,147],"little":[100],"loss":[101],"in":[102,133],"performance.":[103],"It":[104],"significantly":[107],"better":[108],"baseline":[111],"trained":[113],"without":[114],"distillation:":[116],"by":[117],"4.2/1.7":[118],"BLEU":[119],"greedy":[121],"decoding/beam":[122],"search.":[123],"Applying":[124],"weight":[125],"pruning":[126],"top":[128],"results":[132],"has":[138],"13":[139],"fewer":[140],"parameters":[141],"model,":[146],"decrease":[149],"0.4":[151],"BLEU.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":135},{"year":2022,"cited_by_count":106},{"year":2021,"cited_by_count":154},{"year":2020,"cited_by_count":137},{"year":2019,"cited_by_count":81},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}