{"id":"https://openalex.org/W4412888590","doi":"https://doi.org/10.18653/v1/2025.findings-acl.261","title":"A Self-Distillation Recipe for Neural Machine Translation","display_name":"A Self-Distillation Recipe for Neural Machine Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888590","doi":"https://doi.org/10.18653/v1/2025.findings-acl.261"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.261","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.261","pdf_url":"https://aclanthology.org/2025.findings-acl.261.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.261.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101298290","display_name":"Hongfei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongfei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuofei Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuofei Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056590711","display_name":"Qiuhui Liu","orcid":"https://orcid.org/0000-0002-6936-4107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuhui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083881203","display_name":"Lingling Mu","orcid":"https://orcid.org/0000-0001-6556-784X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingling Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5050","last_page":"5064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5321000218391418,"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":0.5321000218391418,"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/recipe","display_name":"Recipe","score":0.9703958630561829},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7497897148132324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072682976722717},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6625884175300598},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5786330103874207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4695839285850525},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10890129208564758},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05971720814704895}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9703958630561829},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7497897148132324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072682976722717},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6625884175300598},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5786330103874207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4695839285850525},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10890129208564758},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05971720814704895},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.261","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.261","pdf_url":"https://aclanthology.org/2025.findings-acl.261.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.261","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.261","pdf_url":"https://aclanthology.org/2025.findings-acl.261.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.5799999833106995,"display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G3732306342","display_name":null,"funder_award_id":"232300421386","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G8081367761","display_name":null,"funder_award_id":"62306284","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8940753486","display_name":null,"funder_award_id":"2023M743189","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888590.pdf","grobid_xml":"https://content.openalex.org/works/W4412888590.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3161239248","https://openalex.org/W258429745","https://openalex.org/W2740181000","https://openalex.org/W2561508161","https://openalex.org/W3123969856","https://openalex.org/W1584543623","https://openalex.org/W2098178683","https://openalex.org/W2740680361","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Self-distillation":[0],"distills":[1],"the":[2,6,22,35,46,74,79,87,90,94,113,121,124,161,202],"deeper":[3],"subnetworks":[4],"to":[5,44,72,108,120,129,135,142,148,157,168,188],"shallower":[7],"sub-networks":[8],"without":[9,175],"using":[10],"an":[11,68],"extra":[12],"teacher":[13,84,91],"model,":[14],"and":[15,67,81,102,137,144],"has":[16],"been":[17],"proven":[18],"effective":[19,200],"in":[20,201],"improving":[21],"performance":[23,167,192],"of":[24,27,49,76],"a":[25,57,61,82,99,104,177],"series":[26],"computer":[28],"vision":[29],"tasks.In":[30],"this":[31],"paper,":[32],"we":[33,97],"study":[34],"representation-based":[36],"self-distillation":[37],"methods":[38],"for":[39],"Neural":[40],"Machine":[41],"Translation":[42],"(NMT)":[43],"avoid":[45],"efficiency":[47],"issue":[48],"probability":[50],"distribution":[51],"based":[52],"Knowledge":[53],"Distillation":[54],"(KD)":[55],"with":[56,179,194,206],"large":[58],"vocabulary.We":[59],"present":[60,103],"rank-order":[62],"augmented":[63],"Pearson":[64],"correlation":[65],"loss":[66],"iterative":[69],"distillation":[70,115,173],"method":[71,107,154,185,197],"prevent":[73,89],"discrepancy":[75],"predictions":[77],"between":[78],"student":[80],"stronger":[83],"from":[85,92],"disturbing":[86],"training.To":[88],"misleading":[93],"student's":[95],"learning,":[96],"utilize":[98],"warm-up":[100],"strategy":[101],"gradient":[105],"adaption":[106],"scale":[109],"down":[110],"or":[111,190,205],"zero":[112],"knowledge":[114,172],"gradients":[116],"which":[117],"are":[118],"opposite":[119],"translation.Experiments":[122],"on":[123],"low-resource":[125],"IWSLT":[126],"14":[127,133,146],"German":[128],"English,":[130],"middle-resource":[131],"WMT":[132,139,145],"English":[134,143,147],"German,":[136],"high-resource":[138],"15":[140],"Czech":[141],"French":[149],"tasks":[150],"show":[151,182],"that":[152,183],"our":[153,184],"can":[155,186],"lead":[156,187],"significant":[158],"improvements":[159],"over":[160],"strong":[162],"Transformer":[163],"baselines,":[164],"obtaining":[165],"comparable":[166,189],"previous":[169],"machine":[170],"translation":[171],"studies":[174],"pre-training":[176],"teacher.Experiments":[178],"shallower/deeper":[180],"Transformers":[181],"better":[191],"efficiently":[193],"fewer":[195],"layers.Our":[196],"is":[198],"also":[199],"multilingual":[203],"setting":[204],"recurrent":[207],"decoder.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}