{"id":"https://openalex.org/W2963684875","doi":"https://doi.org/10.18653/v1/k18-1056","title":"Sequence to Sequence Mixture Model for Diverse Machine Translation","display_name":"Sequence to Sequence Mixture Model for Diverse Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963684875","doi":"https://doi.org/10.18653/v1/k18-1056","mag":"2963684875"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k18-1056","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1056","pdf_url":"https://www.aclweb.org/anthology/K18-1056.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K18-1056.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060320196","display_name":"Xuanli He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Xuanli He","raw_affiliation_strings":["Google Brain","Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","US"],"is_corresponding":true,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Monash University, Australia","Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Mohammad Norouzi","raw_affiliation_strings":["Google Brain","Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081525024"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"592"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9902999997138977,"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":0.7966747283935547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747300863265991},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7459052801132202},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6139811277389526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5831347107887268},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5671356320381165},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5524036288261414},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5492942929267883},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.5055220127105713},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4509333372116089},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4431675970554352},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4359554648399353},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42796117067337036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3702280819416046},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26657241582870483},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13532140851020813}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7966747283935547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747300863265991},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7459052801132202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6139811277389526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831347107887268},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5671356320381165},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5524036288261414},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5492942929267883},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.5055220127105713},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4509333372116089},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4431675970554352},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4359554648399353},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42796117067337036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3702280819416046},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26657241582870483},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13532140851020813},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k18-1056","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1056","pdf_url":"https://www.aclweb.org/anthology/K18-1056.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k18-1056","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1056","pdf_url":"https://www.aclweb.org/anthology/K18-1056.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963684875.pdf","grobid_xml":"https://content.openalex.org/works/W2963684875.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W243301275","https://openalex.org/W1522301498","https://openalex.org/W1862810382","https://openalex.org/W2064675550","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2183341477","https://openalex.org/W2271840356","https://openalex.org/W2525778437","https://openalex.org/W2557436004","https://openalex.org/W2567948266","https://openalex.org/W2579496717","https://openalex.org/W2581377246","https://openalex.org/W2604178507","https://openalex.org/W2744813330","https://openalex.org/W2756978580","https://openalex.org/W2757592053","https://openalex.org/W2794365787","https://openalex.org/W2795601629","https://openalex.org/W2798493043","https://openalex.org/W2949555952","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963537482","https://openalex.org/W2963551569","https://openalex.org/W2963713328","https://openalex.org/W2963913356","https://openalex.org/W2964121744","https://openalex.org/W2964190861","https://openalex.org/W2964308564","https://openalex.org/W3204406378","https://openalex.org/W4297798436","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2794347674","https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056","https://openalex.org/W2997015083","https://openalex.org/W4321065355","https://openalex.org/W2892009878","https://openalex.org/W4379381477","https://openalex.org/W4293577743","https://openalex.org/W3127743011"],"abstract_inverted_index":{"Sequence":[0],"to":[1,16,52,94,115],"sequence":[2,51,53],"(SEQ2SEQ)":[3],"models":[4,21,71],"often":[5],"lack":[6],"diversity":[7,61],"in":[8,22,28],"their":[9],"generated":[10],"translations.":[11],"This":[12],"can":[13],"be":[14],"attributed":[15],"the":[17,41,89,99,108],"limitation":[18],"of":[19,40,68,88,98,110],"SEQ2SEQ":[20,117],"capturing":[23],"lexical":[24],"and":[25,62,132],"syntactic":[26],"variations":[27],"a":[29,49,66,74,95,116],"parallel":[30,100],"corpus":[31],"resulting":[32],"from":[33],"different":[34],"styles,":[35],"genres,":[36],"topics,":[37],"or":[38,121],"ambiguity":[39],"translation":[42,60,70,76],"process.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"develop":[48],"novel":[50],"mixture":[54,79,112,126],"(S2SMIX)":[55],"model":[56,113,127],"that":[57],"improves":[58],"both":[59],"quality":[63],"by":[64],"adopting":[65],"committee":[67],"specialized":[69],"rather":[72],"than":[73],"single":[75],"model.":[77],"Each":[78],"component":[80],"selects":[81],"its":[82],"own":[83],"training":[84],"dataset":[85],"via":[86],"optimization":[87],"marginal":[90],"loglikelihood,":[91],"which":[92],"leads":[93],"soft":[96],"clustering":[97],"corpus.":[101],"Experiments":[102],"on":[103],"four":[104],"language":[105],"pairs":[106],"demonstrate":[107],"superiority":[109],"our":[111],"compared":[114],"baseline":[118],"with":[119],"standard":[120],"diversity-boosted":[122],"beam":[123],"search.":[124],"Our":[125],"uses":[128],"negligible":[129],"additional":[130],"parameters":[131],"incurs":[133],"no":[134],"extra":[135],"computation":[136],"cost":[137],"during":[138],"decoding.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}