{"id":"https://openalex.org/W3036089736","doi":"https://doi.org/10.48550/arxiv.2006.11578","title":"Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy","display_name":"Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy","publication_year":2020,"publication_date":"2020-06-20","ids":{"openalex":"https://openalex.org/W3036089736","doi":"https://doi.org/10.48550/arxiv.2006.11578","mag":"3036089736"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.11578","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11578","pdf_url":"https://arxiv.org/pdf/2006.11578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.11578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016102083","display_name":"Antonio H. O. Fonseca","orcid":"https://orcid.org/0000-0001-7791-8010","observed_orcids":["https://orcid.org/0000-0001-7791-8010"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fonseca, Antonio H. O.","raw_affiliation_strings":["Interdepartmental Neuroscience Program Yale School of Medicine and Dept. of Computer Science New Haven -CT , United States of America","Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdepartmental Neuroscience Program Yale School of Medicine and Dept. of Computer Science New Haven -CT , United States of America","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019679682","display_name":"David van Dijk","orcid":"https://orcid.org/0000-0003-3911-9925","observed_orcids":["https://orcid.org/0000-0003-3911-9925"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"van Dijk, David","raw_affiliation_strings":["Yale School of Medicine and Dept. of Computer Science New Haven -CT , United States of America","Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale School of Medicine and Dept. of Computer Science New Haven -CT , United States of America","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7235999703407288,"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":0.7235999703407288,"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":0.2515000104904175,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009999999776482582,"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/maximum-mean-discrepancy","display_name":"maximum mean discrepancy","score":0.9190000295639038},{"id":"https://openalex.org/keywords/multilingual-word-embeddings","display_name":"multilingual embeddings","score":0.640999972820282}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7701077461242676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374538779258728},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6737644076347351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6598631143569946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6453174352645874},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5652891397476196},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5581251978874207},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.557516872882843},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5192770957946777},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4693288207054138},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43085628747940063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3714017868041992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2093297839164734},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":3,"locations":[{"id":"pmh:oai:arXiv.org:2006.11578","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11578","pdf_url":"https://arxiv.org/pdf/2006.11578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:3036089736","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.11578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.11578","doi":"https://doi.org/10.48550/arxiv.2006.11578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.11578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.11578","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11578","pdf_url":"https://arxiv.org/pdf/2006.11578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3036089736.pdf","grobid_xml":"https://content.openalex.org/works/W3036089736.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2126725946","https://openalex.org/W2183341477","https://openalex.org/W2212660284","https://openalex.org/W2397338926","https://openalex.org/W2471692228","https://openalex.org/W2493916176","https://openalex.org/W2612622926","https://openalex.org/W2626778328","https://openalex.org/W2762484717","https://openalex.org/W2769280657","https://openalex.org/W2786672974","https://openalex.org/W2892266277","https://openalex.org/W2963506925","https://openalex.org/W2969884462","https://openalex.org/W2970045405"],"related_works":["https://openalex.org/W4200212381","https://openalex.org/W2892266277","https://openalex.org/W2899486018","https://openalex.org/W2899189400","https://openalex.org/W2978806756","https://openalex.org/W3155609600","https://openalex.org/W3209501687","https://openalex.org/W3105813095","https://openalex.org/W2140702357","https://openalex.org/W4296052696"],"abstract_inverted_index":{"Word":[0,98],"translation":[1,110],"is":[2,14],"an":[3,75,81],"integral":[4],"part":[5],"of":[6],"language":[7,13],"translation.":[8,50],"In":[9],"machine":[10],"translation,":[11],"each":[12],"considered":[15],"a":[16,39,48,68,113],"domain":[17],"with":[18],"its":[19],"own":[20],"word":[21,26,54,64,85,93,141],"embedding.":[22],"The":[23],"alignment":[24,56,87],"between":[25,120],"embeddings":[27,73,104],"allows":[28],"linking":[29],"semantically":[30],"equivalent":[31],"words":[32,46],"in":[33,74],"multilingual":[34],"contexts.":[35],"Moreover,":[36],"it":[37],"offers":[38],"way":[40],"to":[41],"infer":[42],"cross-lingual":[43],"meaning":[44],"for":[45,53,84],"without":[47],"direct":[49],"Current":[51],"methods":[52,136],"embedding":[55,86],"are":[57,106],"either":[58],"supervised,":[59],"i.e.":[60],"they":[61],"require":[62,91],"known":[63,92,140],"pairs,":[65],"or":[66],"learn":[67],"cross-domain":[69],"transformation":[70],"on":[71,139],"fixed":[72],"unsupervised":[76,131],"way.":[77],"Here":[78],"we":[79],"propose":[80],"end-to-end":[82],"approach":[83],"that":[88,105,125,137],"does":[89],"not":[90,128],"pairs.":[94],"Our":[95],"method,":[96],"termed":[97],"Alignment":[99],"through":[100],"MMD":[101],"(WAM),":[102],"learns":[103],"aligned":[107],"during":[108],"sentence":[109],"training":[111],"using":[112],"localized":[114],"Maximum":[115],"Mean":[116],"Discrepancy":[117],"(MMD)":[118],"constraint":[119],"the":[121],"embeddings.":[122],"We":[123],"show":[124],"our":[126],"method":[127],"only":[129],"out-performs":[130],"methods,":[132],"but":[133],"also":[134],"supervised":[135],"train":[138],"translations.":[142]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2020-06-25T00:00:00"}