{"id":"https://openalex.org/W2963206679","doi":"https://doi.org/10.18653/v1/d18-1549","title":"Phrase-Based & Neural Unsupervised Machine Translation","display_name":"Phrase-Based & Neural Unsupervised Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963206679","doi":"https://doi.org/10.18653/v1/d18-1549","mag":"2963206679"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1549","pdf_url":"https://www.aclweb.org/anthology/D18-1549.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1549.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054371148","display_name":"Guillaume Lample","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Lample","raw_affiliation_strings":["Sorbonne Universits, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","Sorbonne Universit\u00e9s, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universits, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210159731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076248976","display_name":"Myle Ott","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR","IL"],"is_corresponding":false,"raw_author_name":"Myle Ott","raw_affiliation_strings":["Sorbonne Universit\u00e9s","Facebook AI Research","Facebook AI Research Sorbonne Universit\u00e9s","Facebook AI Research Universit\u00e9 Le Mans"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research Universit\u00e9 Le Mans","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068394403","display_name":"Alexis Conneau","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR","IL"],"is_corresponding":false,"raw_author_name":"Alexis Conneau","raw_affiliation_strings":["Facebook AI Research Sorbonne Universit\u00e9s","Facebook AI Research","Facebook AI Research Universit\u00e9 Le Mans","Sorbonne Universit\u00e9s"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research Universit\u00e9 Le Mans","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027101473","display_name":"Ludovic Denoyer","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["Sorbonne Universits, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","Sorbonne Universit\u00e9s, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universits, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s, UPMC Univ Paris 06, CNRS, UMR 7606, LIP6, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210159731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111465122","display_name":"Marc\u2019Aurelio Ranzato","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR","IL"],"is_corresponding":false,"raw_author_name":"Marc\u2019Aurelio Ranzato","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research Universit\u00e9 Le Mans","Sorbonne Universit\u00e9s","Facebook AI Research Sorbonne Universit\u00e9s"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research Universit\u00e9 Le Mans","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Facebook AI Research Sorbonne Universit\u00e9s","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":61.8361,"has_fulltext":true,"cited_by_count":487,"citation_normalized_percentile":{"value":0.99894597,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5039","last_page":"5049"},"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":0.991599977016449,"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":0.8817252516746521},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8538411259651184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7195156812667847},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6483361124992371},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.622614860534668},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6224680542945862},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5988486409187317},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5853069424629211},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5121245384216309},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48079007863998413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.359254390001297},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08030968904495239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8817252516746521},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8538411259651184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7195156812667847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6483361124992371},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.622614860534668},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6224680542945862},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5988486409187317},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5853069424629211},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5121245384216309},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48079007863998413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.359254390001297},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08030968904495239}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1549","pdf_url":"https://www.aclweb.org/anthology/D18-1549.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"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1549","pdf_url":"https://www.aclweb.org/anthology/D18-1549.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":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963206679.pdf","grobid_xml":"https://content.openalex.org/works/W2963206679.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W8895266","https://openalex.org/W38126138","https://openalex.org/W630532510","https://openalex.org/W1508577659","https://openalex.org/W1522301498","https://openalex.org/W1753482797","https://openalex.org/W1915251500","https://openalex.org/W2025768430","https://openalex.org/W2064675550","https://openalex.org/W2121745180","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2134800885","https://openalex.org/W2153579005","https://openalex.org/W2153653739","https://openalex.org/W2157331557","https://openalex.org/W2166880518","https://openalex.org/W2250952810","https://openalex.org/W2251222643","https://openalex.org/W2252106004","https://openalex.org/W2418388682","https://openalex.org/W2425903306","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2546938941","https://openalex.org/W2550821151","https://openalex.org/W2594021297","https://openalex.org/W2595715041","https://openalex.org/W2741602058","https://openalex.org/W2741917668","https://openalex.org/W2785093437","https://openalex.org/W2794365787","https://openalex.org/W2885588803","https://openalex.org/W2950635152","https://openalex.org/W2951184134","https://openalex.org/W2952190837","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2962824887","https://openalex.org/W2963118869","https://openalex.org/W2963216553","https://openalex.org/W2963331137","https://openalex.org/W2963347649","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2963602293","https://openalex.org/W2963993537","https://openalex.org/W2964007535","https://openalex.org/W2964013027","https://openalex.org/W2964121744","https://openalex.org/W2964130895","https://openalex.org/W2964308564","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/W2099607809","https://openalex.org/W170118632","https://openalex.org/W2518299649","https://openalex.org/W2395641992","https://openalex.org/W2251802443","https://openalex.org/W2807475932","https://openalex.org/W4280571180","https://openalex.org/W3021126373","https://openalex.org/W2384400852","https://openalex.org/W3066373881"],"abstract_inverted_index":{"Machine":[0],"translation":[1],"systems":[2],"achieve":[3,151],"near":[4],"human-level":[5],"performance":[6],"on":[7,15],"some":[8],"languages,":[9],"yet":[10],"their":[11,26],"effectiveness":[12],"strongly":[13],"relies":[14],"the":[16,29,71,73,96,106,131,134,161],"availability":[17],"of":[18,21,31,70,76,82,133,163],"large":[19,47],"amounts":[20],"parallel":[22,83,128],"sentences,":[23],"which":[24],"hinders":[25],"applicability":[27],"to":[28,38,40,45],"majority":[30],"language":[32,77],"pairs.":[33],"This":[34],"work":[35],"investigates":[36],"how":[37],"learn":[39],"translate":[41],"when":[42],"having":[43,102],"access":[44],"only":[46],"monolingual":[48],"corpora":[49],"in":[50],"each":[51],"language.":[52],"We":[53],"propose":[54],"two":[55],"model":[56],"variants,":[57],"a":[58,61,67,126],"neural":[59],"and":[60,79,101,111,120,147,157,170],"phrase-based":[62],"model.":[63],"Both":[64],"versions":[65],"leverage":[66],"careful":[68],"initialization":[69],"parameters,":[72],"denoising":[74],"effect":[75],"models":[78,89,116],"automatic":[80],"generation":[81],"data":[84],"by":[85,136],"iterative":[86],"back-translation.":[87],"These":[88],"are":[90],"significantly":[91],"better":[92,153],"than":[93,138,155],"methods":[94,150],"from":[95],"literature,":[97],"while":[98],"being":[99],"simpler":[100],"fewer":[103],"hyper-parameters.":[104],"On":[105,142],"widely":[107],"used":[108],"WMT'14":[109],"English-French":[110],"WMT'16":[112],"German-English":[113],"benchmarks,":[114],"our":[115,149],"respectively":[117],"obtain":[118],"28.1":[119],"25.2":[121],"BLEU":[122,140],"points":[123],"without":[124],"using":[125],"single":[127],"sentence,":[129],"outperforming":[130],"state":[132],"art":[135],"more":[137],"11":[139],"points.":[141],"low-resource":[143],"languages":[144],"like":[145],"English-Urdu":[146],"English-Romanian,":[148],"even":[152],"results":[154],"semisupervised":[156],"supervised":[158],"approaches":[159],"leveraging":[160],"paucity":[162],"available":[164],"bitexts.":[165],"Our":[166],"code":[167],"for":[168],"NMT":[169],"PBSMT":[171],"is":[172],"publicly":[173],"available.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":97},{"year":2020,"cited_by_count":143},{"year":2019,"cited_by_count":112},{"year":2018,"cited_by_count":14}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}