{"id":"https://openalex.org/W4416034019","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1053","title":"TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling","display_name":"TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034019","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1053"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1053","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1053.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1053.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083967421","display_name":"Julien Knafou","orcid":"https://orcid.org/0000-0002-9086-4982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Knafou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049986775","display_name":"Luc Mottin","orcid":"https://orcid.org/0000-0002-9614-9293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luc Mottin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076116299","display_name":"Ana\u00efs Mottaz","orcid":"https://orcid.org/0000-0003-0080-9451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana\u00efs Mottaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008557851","display_name":"Alexandre Flament","orcid":"https://orcid.org/0000-0003-2209-5218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Flament","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042384742","display_name":"Patrick Ruch","orcid":"https://orcid.org/0000-0002-3374-2962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Ruch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.15680647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19338","last_page":"19354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.275299996137619,"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":0.275299996137619,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.15610000491142273,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.11339999735355377,"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/translation","display_name":"Translation (biology)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.40939998626708984},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36169999837875366},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33320000767707825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2937000095844269},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2870999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48649999499320984},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1053","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1053.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"},{"id":"pmh:oai:hesso.tind.io:17049","is_oa":true,"landing_page_url":"https://aclanthology.org/2025.findings-emnlp.1053/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/17049","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1053","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1053.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":[{"id":"https://openalex.org/G1794834023","display_name":"METAPLANTCODE - Harmonization of plant metabarcoding pipelines in Europe to support monitoring activities in the field of plants and their functional organismic networks","funder_award_id":"216811","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320318789","display_name":"Biodiversa+","ror":"https://ror.org/05cvqmv08"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320326610","display_name":"Haute \u00e9cole Sp\u00e9cialis\u00e9e de Suisse Occidentale","ror":"https://ror.org/03r5zec51"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034019.pdf","grobid_xml":"https://content.openalex.org/works/W4416034019.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"scarcity":[1],"of":[2,13,75,98],"non-English":[3],"language":[4,27,84],"data":[5],"in":[6,46,101,111],"specialized":[7],"domains":[8],"significantly":[9],"limits":[10],"the":[11,42,68,71,96],"development":[12],"effective":[14],"Natural":[15],"Language":[16],"Processing":[17],"(NLP)":[18],"tools.We":[19],"present":[20],"Trans-BERT,":[21],"a":[22,37,102],"novel":[23],"framework":[24],"for":[25,89,106],"pre-training":[26,91],"models":[28],"using":[29],"exclusively":[30],"synthetically":[31,64],"translated":[32,65],"text,":[33],"and":[34,86,92],"introduce":[35],"TransCorpus,":[36],"scalable":[38],"translation":[39,100,104],"toolkit.Focusing":[40],"on":[41,54],"life":[43,77],"sciences":[44,78],"domain":[45],"French,":[47],"our":[48],"approach":[49],"demonstrates":[50],"that":[51],"state-of-the-art":[52],"performance":[53],"various":[55],"downstream":[56],"tasks":[57],"can":[58],"be":[59],"achieved":[60],"solely":[61],"by":[62],"leveraging":[63],"data.We":[66],"release":[67],"TransCorpus":[69],"toolkit,":[70],"TransCorpus-bio-fr":[72],"corpus":[73],"(36.4GB":[74],"French":[76],"text),":[79],"TransBERT-bio-fr,":[80],"its":[81],"associated":[82],"pre-trained":[83],"model":[85],"reproducible":[87],"code":[88],"both":[90],"finetuning.Our":[93],"results":[94],"highlight":[95],"viability":[97],"synthetic":[99],"high-resource":[103],"direction":[105],"building":[107],"high-quality":[108],"NLP":[109],"resources":[110],"low-resource":[112],"language/domain":[113],"pairs.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}
