{"id":"https://openalex.org/W4414394662","doi":"https://doi.org/10.3724/2096-7004.di.2025.0109","title":"CoRe-KD: Contrastive Multi-Teacher and Retention-Aware Knowledge Distillation for Continual Multilingual Neural Machine Translation","display_name":"CoRe-KD: Contrastive Multi-Teacher and Retention-Aware Knowledge Distillation for Continual Multilingual Neural Machine Translation","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414394662","doi":"https://doi.org/10.3724/2096-7004.di.2025.0109"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0109","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0109","pdf_url":"https://www.sciengine.com/doi/pdf/FB567064D25C40129F817FFBEBC9C383","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/FB567064D25C40129F817FFBEBC9C383","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100579282","display_name":"Lin Zhou","orcid":"https://orcid.org/0009-0007-1772-2500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Degen Huang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12815469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250109","last_page":"20250109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.996399998664856,"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":0.9534000158309937,"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/machine-translation","display_name":"Machine translation","score":0.7677000164985657},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6991999745368958},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5490999817848206},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.43529999256134033},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4293000102043152},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41290000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997999787330627},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7677000164985657},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6991999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6967999935150146},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6107000112533569},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5963000059127808},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0109","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0109","pdf_url":"https://www.sciengine.com/doi/pdf/FB567064D25C40129F817FFBEBC9C383","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0109","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0109","pdf_url":"https://www.sciengine.com/doi/pdf/FB567064D25C40129F817FFBEBC9C383","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5630136037","display_name":null,"funder_award_id":"2020AAA0108004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414394662.pdf","grobid_xml":"https://content.openalex.org/works/W4414394662.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"longstanding":[1],"objective":[2],"of":[3,78,121],"multilingual":[4],"neural":[5],"machine":[6],"translation":[7,19,45,115],"(MNMT)":[8],"is":[9],"to":[10,13,40,62,82,98,113],"expand":[11],"models":[12],"acquire":[14],"new":[15,36,114],"knowledge":[16,59],"from":[17,101],"incremental":[18],"tasks":[20],"over":[21],"time.":[22],"Existing":[23],"methods":[24],"predominantly":[25],"concentrate":[26],"on":[27,43],"mitigating":[28],"catastrophic":[29],"forgetting":[30],"by":[31],"compromising":[32],"between":[33],"original":[34,122],"and":[35,57,89],"language":[37],"pairs,":[38],"leading":[39],"suboptimal":[41],"performance":[42,120],"both":[44],"tasks.":[46,123],"In":[47],"this":[48],"work,":[49],"we":[50],"propose":[51],"CoRe-KD,":[52],"a":[53,68,90],"novel":[54],"contrastive":[55,69,87],"multi-teacher":[56],"retention-aware":[58],"distillation":[60,71],"method":[61],"prevent":[63],"forgetting.":[64],"Specifically,":[65],"CoRe-KD":[66,110],"introduces":[67],"multiteacher":[70],"strategy":[72],"that":[73,93,109],"assesses":[74],"the":[75,83,95,119],"representational":[76],"relevance":[77],"each":[79],"teacher":[80],"model":[81,85,97],"student":[84,96],"via":[86],"learning,":[88],"retention":[91],"mechanism":[92],"allows":[94],"mimic":[99],"outputs":[100],"previous":[102],"state":[103],"during":[104],"training.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"effectively":[111],"adapts":[112],"directions":[116],"while":[117],"preserving":[118]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}