{"id":"https://openalex.org/W3202167223","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534401","title":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders- Decoders","display_name":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders- Decoders","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3202167223","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534401","mag":"3202167223"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5078591720","display_name":"Junwei Liao","orcid":"https://orcid.org/0000-0001-7321-7583"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junwei Liao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597408","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1872-3429"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Cognitive Services Research Group Microsoft, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Services Research Group Microsoft, Seattle, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640051","display_name":"Ming Gong","orcid":"https://orcid.org/0000-0001-6140-7187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Gong","raw_affiliation_strings":["STCA NLP Group Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"STCA NLP Group Microsoft, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077262995","display_name":"Linjun Shou","orcid":"https://orcid.org/0000-0002-1050-7708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjun Shou","raw_affiliation_strings":["STCA NLP Group Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"STCA NLP Group Microsoft, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021975286","display_name":"Hong Qu","orcid":"https://orcid.org/0000-0001-6114-3441"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Zeng","raw_affiliation_strings":["Cognitive Services Research Group Microsoft, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Services Research Group Microsoft, Seattle, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078591720"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78438102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9997000098228455,"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":0.9958000183105469,"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/machine-translation","display_name":"Machine translation","score":0.9043485522270203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8607050776481628},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6524961590766907},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6188150644302368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5048444867134094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41119885444641113},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4101662039756775}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.9043485522270203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607050776481628},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6524961590766907},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6188150644302368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048444867134094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41119885444641113},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4101662039756775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W11511616","https://openalex.org/W22168010","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2546938941","https://openalex.org/W2550821151","https://openalex.org/W2798465082","https://openalex.org/W2804232614","https://openalex.org/W2807535859","https://openalex.org/W2809456172","https://openalex.org/W2888456631","https://openalex.org/W2899015110","https://openalex.org/W2921280978","https://openalex.org/W2952153923","https://openalex.org/W2962778428","https://openalex.org/W2962807144","https://openalex.org/W2963216553","https://openalex.org/W2963247703","https://openalex.org/W2963250244","https://openalex.org/W2963347649","https://openalex.org/W2963403868","https://openalex.org/W2963499433","https://openalex.org/W2963532001","https://openalex.org/W2963979492","https://openalex.org/W2963983698","https://openalex.org/W2964073484","https://openalex.org/W2964108048","https://openalex.org/W2968917279","https://openalex.org/W2994689640","https://openalex.org/W2997518171","https://openalex.org/W2998458489","https://openalex.org/W3017208877","https://openalex.org/W3033879023","https://openalex.org/W3034469191","https://openalex.org/W3034719878","https://openalex.org/W3035547806","https://openalex.org/W3101577648","https://openalex.org/W3155915431","https://openalex.org/W4287774231","https://openalex.org/W4385245566","https://openalex.org/W6600454326","https://openalex.org/W6600880057","https://openalex.org/W6729383884","https://openalex.org/W6739901393","https://openalex.org/W6752241964","https://openalex.org/W6752527106","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W970670907","https://openalex.org/W2747680751","https://openalex.org/W2753086417","https://openalex.org/W3204726280","https://openalex.org/W1569841287","https://openalex.org/W1538473846","https://openalex.org/W1985007624","https://openalex.org/W2823653893","https://openalex.org/W2351428524"],"abstract_inverted_index":{"Recently,":[0],"universal":[1,16,25,79,99,170],"neural":[2],"machine":[3],"translation":[4,75,87,146,201],"(NMT)":[5],"with":[6,144,214],"shared":[7,54],"encoder-decoder":[8],"gained":[9],"good":[10],"performance":[11,66],"on":[12,73,153,221],"zero-shot":[13,74,86,200],"translation.":[14],"Unlike":[15],"NMT,":[17],"jointly":[18,140,218],"trained":[19,186,217],"language-specific":[20,89,107],"encoders-decoders":[21],"aim":[22],"to":[23,93,139,184],"achieve":[24],"representation":[26,121],"across":[27],"non-shared":[28,41,96],"modules,":[29],"each":[30],"of":[31,46,67,128],"which":[32],"is":[33],"for":[34],"a":[35,134,149,211],"language":[36,38,49,183,206],"or":[37,166],"family.":[39],"The":[40],"architecture":[42,97],"has":[43],"the":[44,53,65,95,103,120,125,142,145,173,185,191,199,215],"advantage":[45],"mitigating":[47],"internal":[48],"competition,":[50],"especially":[51],"when":[52],"vocabulary":[55],"and":[56,71,98,108,114,123,172,207],"model":[57,143,163,187,193,216],"parameters":[58,113],"are":[59],"restricted":[60],"in":[61,148],"their":[62],"size.":[63],"However,":[64],"using":[68,88],"multiple":[69],"encoders":[70],"decoders":[72],"still":[76],"lags":[77],"behind":[78],"NMT.":[80],"In":[81],"this":[82,196,203],"work,":[83],"we":[84,117,178],"study":[85],"encoders-decoders.":[90],"We":[91,131],"propose":[92],"generalize":[94],"NMT":[100,171],"by":[101,188],"differentiating":[102],"Transformer":[104],"layers":[105],"between":[106,202],"interlingua.":[109],"By":[110],"selectively":[111],"sharing":[112],"applying":[115],"cross-attentions,":[116],"explore":[118],"maximizing":[119],"universality":[122],"realizing":[124],"best":[126],"alignment":[127],"language-agnostic":[129],"information.":[130],"also":[132],"introduce":[133],"denoising":[135],"auto-encoding":[136],"(DAE)":[137],"objective":[138],"train":[141],"task":[147],"multi-task":[150],"manner.":[151],"Experiments":[152],"two":[154],"public":[155],"multilingual":[156],"parallel":[157],"datasets":[158],"show":[159],"that":[160],"our":[161],"proposed":[162],"achieves":[164,210],"competitive":[165],"better":[167],"results":[168],"than":[169],"strong":[174],"pivot":[175],"baseline.":[176],"Moreover,":[177],"experiment":[179],"incrementally":[180],"adding":[181],"new":[182,192],"only":[189],"updating":[190],"parameters.":[194],"With":[195],"little":[197],"effort,":[198],"newly":[204],"added":[205],"existing":[208],"languages":[209],"comparable":[212],"result":[213],"from":[219],"scratch":[220],"all":[222],"languages.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}