{"id":"https://openalex.org/W3119184842","doi":"https://doi.org/10.18653/v1/2020.wmt-1.61","title":"Combining Sequence Distillation and Transfer Learning for Efficient Low-Resource Neural Machine Translation Models","display_name":"Combining Sequence Distillation and Transfer Learning for Efficient Low-Resource Neural Machine Translation Models","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3119184842","doi":"https://doi.org/10.18653/v1/2020.wmt-1.61","mag":"3119184842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.61","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.61","pdf_url":"https://aclanthology.org/2020.wmt-1.61.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.61.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","National Institute of Information and Communications Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I46980622","https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101988321","display_name":"Atsushi Fujita","orcid":"https://orcid.org/0000-0003-3799-8428"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","National Institute of Information and Communications Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I46980622","https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"492","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792068600654602},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.790939211845398},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.7906421422958374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6602115631103516},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6528475284576416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6353335976600647},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5860424041748047},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5416946411132812},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5049481987953186},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44327160716056824},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44202086329460144},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4211842119693756},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41637828946113586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3618365526199341},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19461071491241455},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.11092677712440491},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10160753130912781},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08894586563110352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792068600654602},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.790939211845398},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.7906421422958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6602115631103516},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6528475284576416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6353335976600647},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5860424041748047},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5416946411132812},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5049481987953186},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44327160716056824},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44202086329460144},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4211842119693756},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41637828946113586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3618365526199341},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19461071491241455},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.11092677712440491},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10160753130912781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08894586563110352},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.61","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.61","pdf_url":"https://aclanthology.org/2020.wmt-1.61.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"mag:3119184842","is_oa":false,"landing_page_url":"https://aclanthology.org/2020.wmt-1.61/","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.61","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.61","pdf_url":"https://aclanthology.org/2020.wmt-1.61.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7191329359","display_name":"Developing a translation process model and constructing an integrated translation environment through detailed descriptions of translation norms and competences","funder_award_id":"19H05660","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7222400979","display_name":null,"funder_award_id":"JPMI00316","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"}],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119184842.pdf","grobid_xml":"https://content.openalex.org/works/W3119184842.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2286365479","https://openalex.org/W2319920447","https://openalex.org/W2611838487","https://openalex.org/W2744813330","https://openalex.org/W2944815030","https://openalex.org/W2963088995","https://openalex.org/W2963216553","https://openalex.org/W2963247703","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963643655","https://openalex.org/W2963877297","https://openalex.org/W2964084720","https://openalex.org/W2964308564","https://openalex.org/W2985301125","https://openalex.org/W2996844526","https://openalex.org/W3031432954","https://openalex.org/W3037312903","https://openalex.org/W3046158644"],"related_works":["https://openalex.org/W2422843715","https://openalex.org/W2986030184","https://openalex.org/W2895774958","https://openalex.org/W1508577659","https://openalex.org/W3126910220","https://openalex.org/W1915251500","https://openalex.org/W2337363174","https://openalex.org/W3017552862","https://openalex.org/W2399188371","https://openalex.org/W2810533336","https://openalex.org/W2973995485","https://openalex.org/W3036422752","https://openalex.org/W3180103694","https://openalex.org/W2786253471","https://openalex.org/W2951521088","https://openalex.org/W2911689843","https://openalex.org/W3199365283","https://openalex.org/W3202184729","https://openalex.org/W3198071757","https://openalex.org/W2945501029"],"abstract_inverted_index":{"In":[0],"neural":[1],"machine":[2],"translation":[3,44,150],"(NMT),":[4],"sequence":[5],"distillation":[6],"(SD)":[7],"through":[8],"creation":[9],"of":[10,52,128,146,156,159],"distilled":[11,113,137],"corpora":[12,41,70,77,141],"leads":[13],"to":[14],"efficient":[15,58,164],"(compact":[16],"and":[17,54,78,90,139,161],"fast)":[18],"models.However,":[19],"its":[20],"effectiveness":[21],"in":[22,46,123,142],"extremely":[23],"low-resource":[24],"(ELR)":[25],"settings":[26],"has":[27],"not":[28],"been":[29],"well-studied.On":[30],"the":[31,75,93,103,112,136,143,154],"other":[32],"hand,":[33],"transfer":[34],"learning":[35],"(TL)":[36],"by":[37],"leveraging":[38],"larger":[39],"helping":[40,69,140],"greatly":[42],"improves":[43,149],"quality":[45],"general.This":[47],"paper":[48],"investigates":[49],"a":[50],"combination":[51],"SD":[53,160],"TL":[55,67,147,162],"for":[56,61,73,163,167],"training":[57,100],"NMT":[59,165],"models":[60,105],"ELR":[62,76,87,114,138,168],"settings,":[63],"where":[64],"we":[65],"utilize":[66],"with":[68,85,98,106],"twice:":[71],"once":[72],"distilling":[74],"then":[79],"during":[80],"compact":[81,104],"model":[82],"training.We":[83],"experimented":[84],"two":[86],"settings:":[88],"Vietnamese-English":[89],"Hindi-English":[91],"from":[92],"Asian":[94],"Language":[95],"Treebank":[96],"dataset":[97],"18k":[99],"sentence":[101],"pairs.Using":[102],"40%":[107,127],"smaller":[108],"parameters":[109],"trained":[110],"on":[111],"corpora,":[115],"greedy":[116],"search":[117],"achieved":[118],"3.6":[119],"BLEU":[120],"points":[121],"improvement":[122],"average":[124],"while":[125],"reducing":[126],"decoding":[129],"time.We":[130],"also":[131],"confirmed":[132],"that":[133],"using":[134],"both":[135],"second":[144],"round":[145],"further":[148],"quality.Our":[151],"work":[152],"highlights":[153],"importance":[155],"stage-wise":[157],"application":[158],"modeling":[166],"settings.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-01-18T00:00:00"}