{"id":"https://openalex.org/W2905749056","doi":"https://doi.org/10.1162/tacl_a_00288","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","display_name":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","publication_year":2019,"publication_date":"2019-09-11","ids":{"openalex":"https://openalex.org/W2905749056","doi":"https://doi.org/10.1162/tacl_a_00288","mag":"2905749056"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00288","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00288","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00288/1923278/tacl_a_00288.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00288/1923278/tacl_a_00288.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":false,"raw_author_name":"Mikel Artetxe","raw_affiliation_strings":["University of the Basque Country (UPV/EHU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","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"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["Facebook AI Research","Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.046,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98769252,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"597","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T13629","display_name":"Text Readability and Simplification","score":0.9919000267982483,"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":0.8585050106048584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7088323831558228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6775150299072266},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6011751890182495},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5173898935317993},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5061742663383484},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5000507831573486},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46560078859329224},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43149131536483765},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.430780291557312},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12465748190879822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585050106048584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7088323831558228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6775150299072266},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6011751890182495},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5173898935317993},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5061742663383484},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5000507831573486},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46560078859329224},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43149131536483765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.430780291557312},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12465748190879822},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/tacl_a_00288","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00288","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00288/1923278/tacl_a_00288.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"mag:2905749056","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1812.10464","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,"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":"pmh:oai:doaj.org/article:9dbebd9e90f34c40a57b6eb998665289","is_oa":true,"landing_page_url":"https://doaj.org/article/9dbebd9e90f34c40a57b6eb998665289","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 7, Pp 597-610 (2019)","raw_type":"article"},{"id":"doi:10.48550/arxiv.1812.10464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.10464","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,"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":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00288","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00288","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00288/1923278/tacl_a_00288.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W630532510","https://openalex.org/W1486649854","https://openalex.org/W1828724394","https://openalex.org/W1840435438","https://openalex.org/W2126725946","https://openalex.org/W2131744502","https://openalex.org/W2150102617","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2251033195","https://openalex.org/W2251765408","https://openalex.org/W2270364989","https://openalex.org/W2419539795","https://openalex.org/W2550821151","https://openalex.org/W2572474373","https://openalex.org/W2609278920","https://openalex.org/W2626534681","https://openalex.org/W2739740656","https://openalex.org/W2741268430","https://openalex.org/W2741788241","https://openalex.org/W2742155240","https://openalex.org/W2788353357","https://openalex.org/W2794365787","https://openalex.org/W2794557536","https://openalex.org/W2798389157","https://openalex.org/W2798669739","https://openalex.org/W2885323099","https://openalex.org/W2886198413","https://openalex.org/W2887920589","https://openalex.org/W2889326796","https://openalex.org/W2890007195","https://openalex.org/W2891177506","https://openalex.org/W2891555348","https://openalex.org/W2914120296","https://openalex.org/W2923014074","https://openalex.org/W2952444318","https://openalex.org/W2953109491","https://openalex.org/W2962735107","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963090765","https://openalex.org/W2963206679","https://openalex.org/W2963216553","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963672008","https://openalex.org/W2963721344","https://openalex.org/W2963826397","https://openalex.org/W2963846996","https://openalex.org/W2963918774","https://openalex.org/W2964266061","https://openalex.org/W3104723404"],"related_works":["https://openalex.org/W2963341956","https://openalex.org/W2914120296","https://openalex.org/W2550821151","https://openalex.org/W2973088264","https://openalex.org/W2626778328","https://openalex.org/W2250539671","https://openalex.org/W2126725946","https://openalex.org/W2525778437","https://openalex.org/W2950577311","https://openalex.org/W2963672008","https://openalex.org/W2962784628","https://openalex.org/W2962739339","https://openalex.org/W2960374072","https://openalex.org/W2609278920","https://openalex.org/W342285082","https://openalex.org/W2964308564","https://openalex.org/W2953109491","https://openalex.org/W2950133940","https://openalex.org/W2794365787","https://openalex.org/W2561995736"],"abstract_inverted_index":{"We":[0,115],"introduce":[1,117],"an":[2,46],"architecture":[3],"to":[4,14,59,77],"learn":[5,60],"joint":[6],"multilingual":[7,138,153],"sentence":[8,132],"representations":[9],"for":[10,39,142],"93":[11,81],"languages,":[12,41,127],"belonging":[13],"more":[15],"than":[16],"30":[17],"different":[18,24],"families":[19],"and":[20,49,74,102,128,151],"written":[21],"in":[22,88,125,137],"28":[23],"scripts.":[25],"Our":[26,86,146],"system":[27],"uses":[28],"a":[29,34,61,118],"single":[30],"BiLSTM":[31],"encoder":[32],"with":[33,45],"shared":[35],"byte-pair":[36],"encoding":[37],"vocabulary":[38],"all":[40],"which":[42],"is":[43],"coupled":[44],"auxiliary":[47],"decoder":[48],"trained":[50],"on":[51,63],"publicly":[52],"available":[53,157],"parallel":[54,103],"corpora.":[55],"This":[56],"enables":[57],"us":[58],"classifier":[62],"top":[64],"of":[65,79,112,122],"the":[66,80,110,148,152],"resulting":[67],"embeddings":[68,133],"using":[69],"English":[70],"annotated":[71],"data":[72,94,100,107],"only,":[73],"transfer":[75],"it":[76],"any":[78,84],"languages":[82],"without":[83],"modification.":[85],"experiments":[87],"cross-lingual":[89,96],"natural":[90],"language":[91],"inference":[92],"(XNLI":[93],"set),":[95,101],"document":[97],"classification":[98],"(MLDoc":[99],"corpus":[104],"mining":[105],"(BUCC":[106],"set)":[108],"show":[109,129],"effectiveness":[111],"our":[113,131],"approach.":[114],"also":[116],"new":[119],"test":[120,154],"set":[121,155],"aligned":[123],"sentences":[124],"112":[126],"that":[130],"obtain":[134],"strong":[135],"results":[136],"similarity":[139],"search":[140],"even":[141],"low-":[143],"resource":[144],"languages.":[145],"implementation,":[147],"pre-trained":[149],"encoder,":[150],"are":[156],"at":[158],"https://github.com/facebookresearch/LASER":[159],".":[160]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}