{"id":"https://openalex.org/W2979303251","doi":"https://doi.org/10.1109/taslp.2019.2946480","title":"Future-Aware Knowledge Distillation for Neural Machine Translation","display_name":"Future-Aware Knowledge Distillation for Neural Machine Translation","publication_year":2019,"publication_date":"2019-10-09","ids":{"openalex":"https://openalex.org/W2979303251","doi":"https://doi.org/10.1109/taslp.2019.2946480","mag":"2979303251"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2946480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2946480","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100363719","display_name":"Biao Zhang","orcid":"https://orcid.org/0000-0002-4865-7090"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Biao Zhang","raw_affiliation_strings":["Software School, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Software School, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055232825","display_name":"Deyi Xiong","orcid":"https://orcid.org/0000-0002-2353-5038"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Xiong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066326238","display_name":"Jinsong Su","orcid":"https://orcid.org/0000-0001-5606-7122"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Software School, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Software School, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100363719"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":3.6405,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94563469,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"2278","last_page":"2287"},"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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":0.8539033532142639},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8454954624176025},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6621612310409546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6345379948616028},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6192394495010376},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.552286684513092},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49575552344322205},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4952670633792877},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.4933151304721832},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4836805760860443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4792894721031189},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46982264518737793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.466244637966156},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.41720932722091675},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.3519507646560669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539033532142639},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8454954624176025},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6621612310409546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6345379948616028},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6192394495010376},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.552286684513092},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49575552344322205},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4952670633792877},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4933151304721832},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4836805760860443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4792894721031189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46982264518737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.466244637966156},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.41720932722091675},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3519507646560669},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2946480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2946480","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3770443946","display_name":null,"funder_award_id":"61672440","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G595882846","display_name":null,"funder_award_id":"61622209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5972996833","display_name":null,"funder_award_id":"61861130364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7868119958","display_name":null,"funder_award_id":"ZK1024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W222053410","https://openalex.org/W1411230545","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2049872937","https://openalex.org/W2101105183","https://openalex.org/W2106565589","https://openalex.org/W2133564696","https://openalex.org/W2156985047","https://openalex.org/W2160380653","https://openalex.org/W2466062786","https://openalex.org/W2532807140","https://openalex.org/W2587694128","https://openalex.org/W2613904329","https://openalex.org/W2626711914","https://openalex.org/W2740510699","https://openalex.org/W2747545581","https://openalex.org/W2755989362","https://openalex.org/W2758514087","https://openalex.org/W2760713883","https://openalex.org/W2769298630","https://openalex.org/W2886776719","https://openalex.org/W2897983179","https://openalex.org/W2962700074","https://openalex.org/W2962780935","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2963091079","https://openalex.org/W2963315891","https://openalex.org/W2963331137","https://openalex.org/W2963403868","https://openalex.org/W2963599677","https://openalex.org/W2963713328","https://openalex.org/W2963736842","https://openalex.org/W2964034111","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2971452554","https://openalex.org/W2999635570","https://openalex.org/W4298159529","https://openalex.org/W4385245566","https://openalex.org/W6600284362","https://openalex.org/W6607333740","https://openalex.org/W6608792757","https://openalex.org/W6628501728","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6728994513","https://openalex.org/W6733321041","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6743218476","https://openalex.org/W6747302705","https://openalex.org/W6759888656"],"related_works":["https://openalex.org/W2587602790","https://openalex.org/W193726211","https://openalex.org/W2152633844","https://openalex.org/W3140479314","https://openalex.org/W2132122285","https://openalex.org/W3098209986","https://openalex.org/W3204668696","https://openalex.org/W3037986478","https://openalex.org/W2117339222","https://openalex.org/W2610387714"],"abstract_inverted_index":{"Although":[0],"future":[1,49],"context":[2,134],"is":[3,14,73],"widely":[4],"regarded":[5],"useful":[6],"for":[7,69],"word":[8,71,160],"prediction":[9],"in":[10,17,75,86],"machine":[11,24,107],"translation,":[12],"it":[13,21],"quite":[15],"difficult":[16],"practice":[18],"to":[19,37,47,58,102,131],"incorporate":[20],"into":[22,124],"neural":[23,54,89,106,110],"translation.":[25],"In":[26,41],"this":[27,39],"paper,":[28],"we":[29,45],"propose":[30,99],"a":[31,52,76,93],"future-aware":[32,59,67,120],"knowledge":[33,50,94,114],"distillation":[34,95,115],"framework":[35],"(FKD)":[36],"address":[38],"issue.":[40],"the":[42,63,82,87,105,125,129,137,142,152],"FKD":[43],"framework,":[44],"learn":[46],"distill":[48],"from":[51],"backward":[53,88],"language":[55,90,111],"model":[56,91,112],"(teacher)":[57],"vectors":[60,121],"(student)":[61],"during":[62,136],"training":[64],"phase.":[65,139],"The":[66,118],"vector":[68],"each":[70],"position":[72],"computed":[74],"bridge":[77],"network":[78],"and":[79,113,145,159],"optimized":[80],"towards":[81],"corresponding":[83],"hidden":[84],"state":[85],"via":[92],"mechanism.":[96],"We":[97],"further":[98],"an":[100],"algorithm":[101],"jointly":[103],"train":[104],"translation":[108,148,157],"model,":[109],"module":[116],"end-to-end.":[117],"learned":[119],"are":[122],"incorporated":[123],"attention":[126],"layer":[127],"of":[128],"decoder":[130],"provide":[132],"full-range":[133],"information":[135],"decoding":[138],"Experiments":[140],"on":[141],"NIST":[143],"Chinese-English":[144],"WMT":[146],"English-German":[147],"tasks":[149],"show":[150],"that":[151],"proposed":[153],"method":[154],"significantly":[155],"improves":[156],"quality":[158],"alignment.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}