{"id":"https://openalex.org/W2951522086","doi":"https://doi.org/10.18653/v1/p19-1312","title":"Unsupervised Joint Training of Bilingual Word Embeddings","display_name":"Unsupervised Joint Training of Bilingual Word Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951522086","doi":"https://doi.org/10.18653/v1/p19-1312","mag":"2951522086"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1312","pdf_url":"https://www.aclweb.org/anthology/P19-1312.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1312.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Benjamin Marie","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101988321","display_name":"Atsushi Fujita","orcid":"https://orcid.org/0000-0003-3799-8428"},"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":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101488996"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81948924,"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":"3224","last_page":"3230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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":0.7946138381958008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7485887408256531},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6774462461471558},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.602343738079071},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.558838427066803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5505268573760986},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5002672672271729},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4422295093536377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4351833760738373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3443993330001831},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10381832718849182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946138381958008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7485887408256531},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6774462461471558},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.602343738079071},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.558838427066803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5505268573760986},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5002672672271729},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4422295093536377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4351833760738373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3443993330001831},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10381832718849182},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1312","pdf_url":"https://www.aclweb.org/anthology/P19-1312.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1312","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1312","pdf_url":"https://www.aclweb.org/anthology/P19-1312.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951522086.pdf","grobid_xml":"https://content.openalex.org/works/W2951522086.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2126725946","https://openalex.org/W2141440284","https://openalex.org/W2148708890","https://openalex.org/W2153579005","https://openalex.org/W2251765408","https://openalex.org/W2493916176","https://openalex.org/W2572114121","https://openalex.org/W2611838487","https://openalex.org/W2798931235","https://openalex.org/W2890007195","https://openalex.org/W2962795068","https://openalex.org/W2963047628","https://openalex.org/W2963165489","https://openalex.org/W2963206679","https://openalex.org/W2963443683","https://openalex.org/W2964266061","https://openalex.org/W4294170691","https://openalex.org/W4299579390"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W2950396480","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338"],"abstract_inverted_index":{"State-of-the-art":[0],"methods":[1],"for":[2,111],"unsupervised":[3,26,56,65,87,93],"bilingual":[4,20],"word":[5,16,40],"embeddings":[6,17],"(BWE)":[7],"train":[8,75,116],"a":[9,19,51],"mapping":[10,27],"function":[11],"that":[12,54,70,73,86],"maps":[13],"pre-trained":[14],"monolingual":[15],"into":[18],"space.":[21],"Despite":[22],"its":[23],"remarkable":[24],"results,":[25],"is":[28],"also":[29],"well-known":[30],"to":[31,43,80,115],"be":[32,44],"limited":[33],"by":[34,109],"the":[35,38,104],"dissimilarity":[36],"between":[37],"original":[39],"embedding":[41],"spaces":[42],"mapped.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"propose":[50],"new":[52],"approach":[53],"trains":[55],"BWE":[57,76,88,95],"jointly":[58,74,89],"on":[59,126],"synthetic":[60],"parallel":[61],"data":[62,83],"generated":[63],"through":[64],"machine":[66],"translation.":[67],"We":[68,102],"demonstrate":[69],"existing":[71],"algorithms":[72],"are":[77],"very":[78],"robust":[79],"noisy":[81],"training":[82],"and":[84,113,122,129],"show":[85],"trained":[90],"significantly":[91],"outperform":[92],"mapped":[94],"in":[96],"several":[97],"cross-lingual":[98],"NLP":[99],"tasks.":[100],"13":[101],"used":[103],"News":[105],"Commentary":[106],"corpora":[107],"provided":[108],"WMT":[110],"ende":[112],"enfr":[114],"SMT":[117],"systems":[118],"performing":[119],"at":[120],"15.4":[121],"20.1":[123],"BLEU":[124],"points":[125],"Newstest2016":[127],"en-de":[128],"Newstest2014":[130],"en-fr,":[131],"respectively.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}