{"id":"https://openalex.org/W3145583208","doi":"https://doi.org/10.1145/3418059","title":"Unsupervised Neural Machine Translation for Similar and Distant Language Pairs","display_name":"Unsupervised Neural Machine Translation for Similar and Distant Language Pairs","publication_year":2021,"publication_date":"2021-01-31","ids":{"openalex":"https://openalex.org/W3145583208","doi":"https://doi.org/10.1145/3418059","mag":"3145583208"},"language":"en","primary_location":{"id":"doi:10.1145/3418059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3418059","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information 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/A5023868584","display_name":"Haipeng Sun","orcid":"https://orcid.org/0000-0002-5899-0401"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haipeng Sun","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431149","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-8007-2503"},"institutions":[{"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":"Rui Wang","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021667085","display_name":"Masao Utiyama","orcid":"https://orcid.org/0000-0003-1111-9245"},"institutions":[{"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":"Masao Utiyama","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488996","display_name":"Benjamin Marie","orcid":"https://orcid.org/0000-0002-5228-2762"},"institutions":[{"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":"Benjamin Marie","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006323375","display_name":"Kehai Chen","orcid":"https://orcid.org/0000-0002-4346-7618"},"institutions":[{"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":"Kehai Chen","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033318800","display_name":"Eiichiro Sumita","orcid":"https://orcid.org/0000-0002-1028-4399"},"institutions":[{"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":"Eiichiro Sumita","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5023868584"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82820713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"17"},"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":0.9994000196456909,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9718000292778015,"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":0.8376241326332092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8218756318092346},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6640235185623169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6631448268890381},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6582561731338501},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5536457300186157},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5052915215492249},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.4839096963405609},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45274433493614197},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4211381673812866},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4148622751235962},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2174791395664215}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8376241326332092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218756318092346},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6640235185623169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6631448268890381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6582561731338501},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5536457300186157},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5052915215492249},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.4839096963405609},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45274433493614197},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4211381673812866},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4148622751235962},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2174791395664215},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3418059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3418059","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1095544304","https://openalex.org/W2036291627","https://openalex.org/W2162245945","https://openalex.org/W2493916176","https://openalex.org/W2560674852","https://openalex.org/W2602856279","https://openalex.org/W2623037479","https://openalex.org/W2788988616","https://openalex.org/W2886095922","https://openalex.org/W2890007195","https://openalex.org/W2932618389","https://openalex.org/W2950428495","https://openalex.org/W2963047628","https://openalex.org/W2963206679","https://openalex.org/W2963216553","https://openalex.org/W2963260202","https://openalex.org/W2963443683","https://openalex.org/W2963532104","https://openalex.org/W2963661253","https://openalex.org/W2963804993","https://openalex.org/W2963922633","https://openalex.org/W2964013027","https://openalex.org/W2964266061","https://openalex.org/W2964707311","https://openalex.org/W2971254483","https://openalex.org/W2997574889"],"related_works":["https://openalex.org/W2566847733","https://openalex.org/W1559710535","https://openalex.org/W2010336863","https://openalex.org/W2962780935","https://openalex.org/W3204448004","https://openalex.org/W4378619223","https://openalex.org/W193726211","https://openalex.org/W2027317339","https://openalex.org/W2532807140","https://openalex.org/W2794347674"],"abstract_inverted_index":{"Unsupervised":[0],"neural":[1,219],"machine":[2,220],"translation":[3,60,133,148,176],"(UNMT)":[4],"has":[5],"achieved":[6],"remarkable":[7],"results":[8,223],"for":[9,46,62,71,120,135,181,224],"several":[10,106],"language":[11,49,64,73,122,139,183,227],"pairs,":[12,184],"such":[13],"as":[14],"French\u2013English":[15],"and":[16,85,112,163,206],"German\u2013English.":[17],"Most":[18],"previous":[19],"studies":[20,28],"have":[21,29],"focused":[22],"on":[23,35,101,214],"modeling":[24],"UNMT":[25,34,45,58,95,119,143,236],"systems;":[26],"few":[27,155],"investigated":[30],"the":[31,55,80,90,116,173,193],"effect":[32],"of":[33,57,82,118,149,175],"specific":[36],"languages.":[37],"In":[38],"this":[39],"article,":[40],"we":[41,104,125,200],"first":[42],"empirically":[43,77],"investigate":[44],"four":[47,138,226],"diverse":[48],"pairs":[50,65,74,228],"(French/German/Chinese/Japanese\u2013English).":[51],"We":[52,76],"confirm":[53],"that":[54,79,93,209,230],"performance":[56,117,134,174],"in":[59,98,177],"tasks":[61],"similar":[63],"(French/German\u2013English)":[66],"is":[67],"dramatically":[68,187],"better":[69],"than":[70],"distant":[72,121,182],"(Chinese/Japanese\u2013English).":[75],"show":[78,229],"lack":[81],"shared":[83,110,164,169],"words":[84,111],"different":[86],"word":[87],"orderings":[88],"are":[89],"main":[91],"reasons":[92],"lead":[94],"to":[96,114,131,159],"underperform":[97],"Chinese/Japanese\u2013English.":[99],"Based":[100],"these":[102,137,198,225],"findings,":[103],"propose":[105,126,201],"methods,":[107],"including":[108],"artificial":[109],"pre-ordering,":[113],"improve":[115,132],"pairs.":[123,140],"Moreover,":[124],"a":[127,147,150,154,160,202],"simple":[128],"general":[129],"method":[130],"all":[136],"The":[141],"existing":[142],"model":[144],"can":[145],"generate":[146],"reasonable":[151],"quality":[152],"after":[153],"training":[156,194],"epochs":[157],"owing":[158],"denoising":[161,186],"mechanism":[162],"latent":[165,170],"representations.":[166],"However,":[167],"learning":[168],"representations":[171],"restricts":[172],"both":[178],"directions,":[179],"particularly":[180],"while":[185],"delays":[188],"convergence":[189],"by":[190],"continuously":[191],"modifying":[192],"data.":[195],"To":[196],"avoid":[197],"problems,":[199],"simple,":[203],"yet":[204],"effective":[205],"efficient,":[207],"approach":[208],"(like":[210],"UNMT)":[211],"relies":[212],"solely":[213],"monolingual":[215],"corpora:":[216],"pseudo-data-based":[217],"unsupervised":[218],"translation.":[221],"Experimental":[222],"our":[231],"proposed":[232],"methods":[233],"significantly":[234],"outperform":[235],"baselines.":[237]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}