{"id":"https://openalex.org/W4416034505","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1236","title":"Assessing the Role of Data Quality in Training Bilingual Language Models","display_name":"Assessing the Role of Data Quality in Training Bilingual Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034505","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1236"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1236","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1236.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1236.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059839283","display_name":"Skyler Seto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Skyler Seto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017591085","display_name":"Maartje ter Hoeve","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maartje Ter Hoeve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031334559","display_name":"Maureen de Seyssel","orcid":"https://orcid.org/0000-0003-2345-5676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maureen de Seyssel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Grangier","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43346328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22694","last_page":"22720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.6829000115394592,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.6829000115394592,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.12110000103712082,"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":0.026200000196695328,"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/training","display_name":"Training (meteorology)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4203999936580658},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.3587000072002411},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3255999982357025},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.31529998779296875},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.30390000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.515500009059906},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4203999936580658},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40389999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C166007726","wikidata":"https://www.wikidata.org/wiki/Q4536542","display_name":"Language assessment","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1236","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1236.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1236","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1236","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1236.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034505.pdf","grobid_xml":"https://content.openalex.org/works/W4416034505.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bilingual":[0],"and":[1,16,61,108,117,136],"multilingual":[2,134],"language":[3,63],"models":[4],"offer":[5,137],"a":[6,76,86,138],"promising":[7],"path":[8],"toward":[9],"scaling":[10],"NLP":[11],"systems":[12],"across":[13],"diverse":[14],"languages":[15,24,32,38],"users.However,":[17],"their":[18],"performance":[19,35,80,114,121],"often":[20],"varies":[21],"wildly":[22],"between":[23],"as":[25,40],"prior":[26],"works":[27],"show":[28],"that":[29,67],"adding":[30],"more":[31,46],"can":[33],"degrade":[34],"for":[36,141],"some":[37],"(such":[39],"English),":[41],"while":[42],"improving":[43],"others":[44],"(typically":[45],"data":[47,69,73,90,98,131],"constrained":[48],"languages).In":[49],"this":[50],"work,":[51],"we":[52],"investigate":[53],"causes":[54],"of":[55,79,130],"these":[56],"inconsistencies":[57],"by":[58,115],"comparing":[59],"bilingual":[60,83,96,119],"monolingual":[62,113],"models.Our":[64],"analysis":[65],"reveals":[66],"unequal":[68],"quality,":[70],"not":[71],"just":[72],"quantity,":[74],"is":[75],"major":[77],"driver":[78],"degradation":[81],"in":[82,133],"settings.We":[84],"propose":[85],"simple":[87],"yet":[88],"effective":[89],"filtering":[91],"strategy":[92],"to":[93,105,123],"select":[94],"higher-quality":[95],"training":[97],"with":[99],"only":[100],"high":[101],"quality":[102,132],"English":[103],"data.Applied":[104],"French,":[106],"German,":[107],"Chinese,":[109],"our":[110],"approach":[111],"improves":[112],"2-4%":[116],"reduces":[118],"model":[120],"gaps":[122],"1%.These":[124],"results":[125],"highlight":[126],"the":[127],"overlooked":[128],"importance":[129],"pretraining":[135],"practical":[139],"recipe":[140],"balancing":[142],"performance.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}