{"id":"https://openalex.org/W2890007195","doi":"https://doi.org/10.18653/v1/d18-1399","title":"Unsupervised Statistical Machine Translation","display_name":"Unsupervised Statistical Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890007195","doi":"https://doi.org/10.18653/v1/d18-1399","mag":"2890007195"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1399","pdf_url":"https://www.aclweb.org/anthology/D18-1399.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1399.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023341622","display_name":"Mikel Artetxe","orcid":null},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mikel Artetxe","raw_affiliation_strings":["IXA NLP Group University of the Basque Country (UPV/EHU)"],"affiliations":[{"raw_affiliation_string":"IXA NLP Group University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037338094","display_name":"Gorka Labaka","orcid":"https://orcid.org/0000-0003-4611-2502"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gorka Labaka","raw_affiliation_strings":["IXA NLP Group University of the Basque Country (UPV/EHU)"],"affiliations":[{"raw_affiliation_string":"IXA NLP Group University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047151336","display_name":"Eneko Agirre","orcid":"https://orcid.org/0000-0002-0195-4899"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eneko Agirre","raw_affiliation_strings":["IXA NLP Group University of the Basque Country (UPV/EHU)"],"affiliations":[{"raw_affiliation_string":"IXA NLP Group University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023341622"],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":37.7372,"has_fulltext":true,"cited_by_count":324,"citation_normalized_percentile":{"value":0.99761482,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3632","last_page":"3642"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9768000245094299,"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/computer-science","display_name":"Computer science","score":0.8901309967041016},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8587790131568909},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.7656103372573853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7571691274642944},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.6658806800842285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6436878442764282},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.629909336566925},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5219513773918152},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4723038673400879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40979087352752686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33959102630615234},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.327347993850708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8901309967041016},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8587790131568909},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.7656103372573853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7571691274642944},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.6658806800842285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6436878442764282},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.629909336566925},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5219513773918152},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4723038673400879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40979087352752686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33959102630615234},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.327347993850708},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1399","pdf_url":"https://www.aclweb.org/anthology/D18-1399.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.01272","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.01272","pdf_url":"https://arxiv.org/pdf/1809.01272","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:addi.ehu.eus:10810/69988","is_oa":true,"landing_page_url":"http://hdl.handle.net/10810/69988","pdf_url":null,"source":{"id":"https://openalex.org/S4306401964","display_name":"Communities in ADDI (University of the Basque Country)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169108374","host_organization_name":"University of the Basque Country","host_organization_lineage":["https://openalex.org/I169108374"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.4230/lipics.time.2019.17","is_oa":true,"landing_page_url":"https://doi.org/10.4230/lipics.time.2019.17","pdf_url":null,"source":{"id":"https://openalex.org/S7407052059","display_name":"Dagstuhl Research Online Publication Server","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1399","pdf_url":"https://www.aclweb.org/anthology/D18-1399.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321764","display_name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","ror":"https://ror.org/03nc27g21"},{"id":"https://openalex.org/F4320321919","display_name":"Euskal Herriko Unibertsitatea","ror":"https://ror.org/000xsnr85"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890007195.pdf","grobid_xml":"https://content.openalex.org/works/W2890007195.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2097333193","https://openalex.org/W2103042430","https://openalex.org/W2121745180","https://openalex.org/W2126725946","https://openalex.org/W2141440284","https://openalex.org/W2146574666","https://openalex.org/W2148708890","https://openalex.org/W2153579005","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2250600644","https://openalex.org/W2250640401","https://openalex.org/W2293547632","https://openalex.org/W2578451281","https://openalex.org/W2740132093","https://openalex.org/W2741602058","https://openalex.org/W2760424551","https://openalex.org/W2788353357","https://openalex.org/W2962824887","https://openalex.org/W2963118869","https://openalex.org/W2963216553","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2963602293","https://openalex.org/W2964013027","https://openalex.org/W2964266061","https://openalex.org/W4241645538","https://openalex.org/W4294170691","https://openalex.org/W4298393544","https://openalex.org/W4299579390","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3204448004","https://openalex.org/W2122287718","https://openalex.org/W2587602790","https://openalex.org/W2740094425","https://openalex.org/W2566847733","https://openalex.org/W193726211","https://openalex.org/W3196981096","https://openalex.org/W2962780935","https://openalex.org/W2131079305","https://openalex.org/W2771528947"],"abstract_inverted_index":{"While":[0],"modern":[1],"machine":[2],"translation":[3],"has":[4,15],"relied":[5],"on":[6,62,156],"large":[7],"parallel":[8],"corpora,":[9],"a":[10,88],"recent":[11],"line":[12],"of":[13,35,83,137],"work":[14],"managed":[16],"to":[17,159],"train":[18],"Neural":[19],"Machine":[20,65],"Translation":[21,66],"(NMT)":[22],"systems":[23,42],"from":[24,79,91],"monolingual":[25,92],"corpora":[26,93],"only":[27],"(Artetxe":[28],"et":[29],"al.,":[30],"2018c;":[31],"Despite":[32],"the":[33,71,80,149],"potential":[34],"this":[36,54],"approach":[37,60],"for":[38,121],"low-resource":[39],"settings,":[40],"existing":[41],"are":[43],"far":[44],"behind":[45],"their":[46,50],"supervised":[47,74,152],"counterparts,":[48],"limiting":[49],"practical":[51],"interest.":[52],"In":[53,113],"paper,":[55],"we":[56,85],"propose":[57],"an":[58,101,109,135],"alternative":[59],"based":[61],"phrase-based":[63],"Statistical":[64],"(SMT)":[67],"that":[68],"significantly":[69],"closes":[70],"gap":[72,150],"with":[73,100,151],"systems.":[75],"Our":[76,163],"method":[77],"profits":[78],"modular":[81],"architecture":[82],"SMT:":[84],"first":[86],"induce":[87],"phrase":[89],"table":[90],"through":[94,108],"cross-lingual":[95],"embedding":[96],"mappings,":[97],"combine":[98],"it":[99],"n-gram":[102],"language":[103],"model,":[104],"and":[105,124,132,147],"fine-tune":[106],"hyperparameters":[107],"unsupervised":[110,145],"MERT":[111],"variant.":[112],"addition,":[114],"iterative":[115],"backtranslation":[116],"improves":[117],"results":[118],"further,":[119],"yielding,":[120],"instance,":[122],"14.08":[123],"26.22":[125],"BLEU":[126,141,161],"points":[127,142],"in":[128],"WMT":[129],"2014":[130],"English-German":[131],"English-French,":[133],"respectively,":[134],"improvement":[136],"more":[138],"than":[139],"7-10":[140],"over":[143],"previous":[144],"systems,":[146],"closing":[148],"SMT":[153],"(Moses":[154],"trained":[155],"Europarl)":[157],"down":[158],"2-5":[160],"points.":[162],"implementation":[164],"is":[165],"available":[166],"at":[167],"https://":[168],"github.com/artetxem/monoses.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":49},{"year":2020,"cited_by_count":100},{"year":2019,"cited_by_count":67},{"year":2018,"cited_by_count":7}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
