{"id":"https://openalex.org/W4398152782","doi":"https://doi.org/10.1109/taslp.2024.3402064","title":"EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning","display_name":"EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4398152782","doi":"https://doi.org/10.1109/taslp.2024.3402064"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3402064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402064","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017982536","display_name":"Zhuoyuan Mao","orcid":"https://orcid.org/0000-0001-5273-2738"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhuoyuan Mao","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028836340","display_name":"Sadao Kurohashi","orcid":"https://orcid.org/0000-0001-5398-8399"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadao Kurohashi","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017982536"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":1.0715,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79921109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2841","last_page":"2856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9731000065803528,"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":0.9731000065803528,"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":0.9682000279426575,"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/T12031","display_name":"Speech and dialogue systems","score":0.9559999704360962,"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/embedding","display_name":"Embedding","score":0.5821572542190552},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5722461342811584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5571251511573792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32745951414108276}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5821572542190552},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5722461342811584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5571251511573792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32745951414108276}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3402064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402064","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2064675550","https://openalex.org/W2150102617","https://openalex.org/W2211192759","https://openalex.org/W2251627854","https://openalex.org/W2609278920","https://openalex.org/W2742155240","https://openalex.org/W2759183967","https://openalex.org/W2885323099","https://openalex.org/W2886198413","https://openalex.org/W2891177506","https://openalex.org/W2891475925","https://openalex.org/W2891555348","https://openalex.org/W2896457183","https://openalex.org/W2949303037","https://openalex.org/W2962735107","https://openalex.org/W2962784628","https://openalex.org/W2963149412","https://openalex.org/W2963250244","https://openalex.org/W2963672008","https://openalex.org/W2963918774","https://openalex.org/W2963979492","https://openalex.org/W2965538726","https://openalex.org/W2970618241","https://openalex.org/W2970641574","https://openalex.org/W2971031524","https://openalex.org/W2973088264","https://openalex.org/W2978017171","https://openalex.org/W2997327944","https://openalex.org/W3034457371","https://openalex.org/W3034999214","https://openalex.org/W3035016936","https://openalex.org/W3035207248","https://openalex.org/W3035390927","https://openalex.org/W3038033387","https://openalex.org/W3039695075","https://openalex.org/W3100652389","https://openalex.org/W3100806282","https://openalex.org/W3100880133","https://openalex.org/W3105966348","https://openalex.org/W3114537677","https://openalex.org/W3152788712","https://openalex.org/W3156636935","https://openalex.org/W3169369929","https://openalex.org/W3173188814","https://openalex.org/W3173783447","https://openalex.org/W3175362188","https://openalex.org/W3175710106","https://openalex.org/W3176047188","https://openalex.org/W3194782062","https://openalex.org/W3212833915","https://openalex.org/W4205756254","https://openalex.org/W4288089799","https://openalex.org/W4310923309","https://openalex.org/W4364383768","https://openalex.org/W4385245566","https://openalex.org/W4385570594","https://openalex.org/W4385572035","https://openalex.org/W4385572261","https://openalex.org/W4385574070","https://openalex.org/W4385574194","https://openalex.org/W4386566675","https://openalex.org/W4386576838","https://openalex.org/W4386784623","https://openalex.org/W6600880057","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6681875376","https://openalex.org/W6685005437","https://openalex.org/W6717262007","https://openalex.org/W6731744468","https://openalex.org/W6743384090","https://openalex.org/W6746023985","https://openalex.org/W6748176785","https://openalex.org/W6751459940","https://openalex.org/W6762521896","https://openalex.org/W6767737316","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6772374981","https://openalex.org/W6776538870","https://openalex.org/W6778231687","https://openalex.org/W6779271971","https://openalex.org/W6781137661","https://openalex.org/W6787937406","https://openalex.org/W6789500345","https://openalex.org/W6847303613","https://openalex.org/W6856605143","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Massively":[0],"multilingual":[1,55],"sentence":[2,56,108,142],"representation":[3],"models,":[4],"e.g.,":[5],"LASER,":[6],"SBERT-distill,":[7],"and":[8,43,52,64,87,114,122,138],"LaBSE,":[9],"help":[10],"significantly":[11,83,98],"improve":[12],"cross-lingual":[13,60,107,111],"downstream":[14],"tasks.":[15],"However,":[16],"the":[17,75,95,120,128,133,139],"use":[18],"of":[19,23,124,127],"a":[20,35],"large":[21],"amount":[22],"data":[24],"or":[25,101],"inefficient":[26],"model":[27,37,77,97,136],"architectures":[28],"results":[29,92,103],"in":[30],"heavy":[31],"computation":[32,89],"to":[33,39,106],"train":[34],"new":[36],"according":[38],"our":[40],"preferred":[41],"languages":[42,148],"domains.":[44],"To":[45],"resolve":[46],"this":[47],"issue,":[48],"we":[49],"introduce":[50],"efficient":[51],"effective":[53],"massively":[54],"embedding":[57,143],"(EMS),":[58],"using":[59,82],"token-level":[61],"reconstruction":[62],"(XTR)":[63],"sentence-level":[65],"contrastive":[66],"learning":[67],"as":[68],"training":[69,137],"objectives.":[70],"Compared":[71],"with":[72,104],"related":[73],"studies,":[74],"proposed":[76,96,129],"can":[78],"be":[79],"efficiently":[80],"trained":[81],"fewer":[84],"parallel":[85],"sentences":[86],"GPU":[88],"resources.":[90],"Empirical":[91],"showed":[93],"that":[94],"yields":[99],"better":[100],"comparable":[102],"regard":[105],"retrieval,":[109],"zero-shot":[110],"genre":[112],"classification,":[113],"sentiment":[115],"classification.":[116],"Ablative":[117],"analyses":[118],"demonstrated":[119],"efficiency":[121],"effectiveness":[123],"each":[125],"component":[126],"model.":[130],"We":[131],"release":[132],"codes":[134],"for":[135],"EMS":[140],"pre-trained":[141],"model,":[144],"which":[145],"supports":[146],"62":[147],"(":[149],"<uri":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Mao-KU/EMS</uri>":[152],").":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}