{"id":"https://openalex.org/W7131660417","doi":"https://doi.org/10.48550/arxiv.2602.21543","title":"Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment","display_name":"Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131660417","doi":"https://doi.org/10.48550/arxiv.2602.21543"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.21543","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126933679","display_name":"Barah Fazili","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fazili, Barah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125704338","display_name":"Koustava Goswami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goswami, Koustava","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10028","display_name":"Topic Modeling","score":0.7398999929428101,"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":0.7398999929428101,"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":0.08380000293254852,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.06679999828338623,"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/parallel-corpora","display_name":"Parallel corpora","score":0.6916999816894531},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6424999833106995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6233999729156494},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4912000000476837},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46149998903274536},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4025999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371000289916992},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6916999816894531},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6913999915122986},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6409000158309937},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6233999729156494},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46149998903274536},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45680001378059387},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.21543","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.21543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21543","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.21543","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.8093239068984985,"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"pretraining":[1],"typically":[2],"lacks":[3],"explicit":[4],"alignment":[5,11,28,77],"signals,":[6],"leading":[7],"to":[8,83,130,163],"suboptimal":[9],"cross-lingual":[10,27,45,76,171],"in":[12,34],"the":[13,97,167],"representation":[14],"space.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"show":[20],"that":[21],"training":[22,115],"standard":[23],"pretrained":[24,177],"models":[25,175],"for":[26,47,66,93,101,113,174,178],"with":[29,155],"a":[30,35,52,67,109,141,152],"multi-way":[31,53,110,156,170],"parallel":[32,54,111,134],"corpus":[33,112],"diverse":[36],"pool":[37,68,142],"of":[38,58,69,143,169],"languages":[39,72,92],"can":[40],"substantially":[41],"improve":[42],"multilingual":[43,104],"and":[44,73,90,103,126],"representations":[46],"NLU":[48],"tasks.":[49],"We":[50],"construct":[51],"dataset":[55,154],"using":[56],"translations":[57],"English":[59],"text":[60],"from":[61,96,140],"an":[62],"off-the-shelf":[63],"NMT":[64],"model":[65,150],"six":[70],"target":[71,145],"achieve":[74],"strong":[75],"through":[78],"contrastive":[79,114],"learning.":[80],"This":[81],"leads":[82],"substantial":[84,117],"performance":[85],"gains":[86,118],"across":[87],"both":[88],"seen":[89],"unseen":[91],"multiple":[94,144],"tasks":[95],"MTEB":[98],"benchmark":[99],"evaluated":[100],"XLM-Roberta":[102],"BERT":[105],"base":[106],"models.":[107],"Using":[108],"yields":[116],"on":[119,151],"bitext":[120,160],"mining":[121,161],"(21.3%),":[122],"semantic":[123],"similarity":[124],"(5.3%),":[125],"classification":[127],"(28.4%)":[128],"compared":[129,162],"English-centric":[131],"(En-X)":[132],"bilingually":[133],"data,":[135],"where":[136],"X":[137],"is":[138],"sampled":[139],"languages.":[146],"Furthermore,":[147],"finetuning":[148],"mE5":[149],"small":[153],"parallelism":[157],"significantly":[158],"improves":[159],"one":[164],"without,":[165],"underscoring":[166],"importance":[168],"supervision":[172],"even":[173],"already":[176],"high-quality":[179],"sentence":[180],"embeddings.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-27T00:00:00"}