{"id":"https://openalex.org/W4416035072","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1766","title":"Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains","display_name":"Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035072","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1766"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1766","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1766","pdf_url":"https://aclanthology.org/2025.emnlp-main.1766.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1766.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100360494","display_name":"Junghwan Kim","orcid":"https://orcid.org/0000-0002-7275-769X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junghwan Kim","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392954","display_name":"Haotian Zhang","orcid":"https://orcid.org/0000-0001-7786-389X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Zhang","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046126345","display_name":"David Jurgens","orcid":"https://orcid.org/0000-0002-2135-9878"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jurgens","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29215477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34855","last_page":"34880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9911999702453613,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9911999702453613,"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":0.0019000000320374966,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.000699999975040555,"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":0.590399980545044},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5683000087738037},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3628000020980835},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29919999837875366},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.2904999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721000075340271},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5296000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505299985408783},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4099000096321106},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1766","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1766","pdf_url":"https://aclanthology.org/2025.emnlp-main.1766.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1766","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1766","pdf_url":"https://aclanthology.org/2025.emnlp-main.1766.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035072.pdf","grobid_xml":"https://content.openalex.org/works/W4416035072.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Authorship":[0],"representation":[1],"(AR)":[2],"learning,":[3],"which":[4,53,70],"models":[5,35],"an":[6,104],"author's":[7],"unique":[8],"writing":[9],"style,":[10],"has":[11,21],"demonstrated":[12],"strong":[13],"performance":[14],"in":[15,27,96,116,148],"authorship":[16],"attribution":[17],"tasks.However,":[18],"prior":[19],"research":[20],"primarily":[22],"focused":[23],"on":[24,59,81,134],"monolingual":[25,94,130],"settings-mostly":[26],"English-leaving":[28],"the":[29,55,138,149],"potential":[30],"benefits":[31],"of":[32,99,108,114,140],"multilingual":[33,42],"AR":[34,43],"underexplored.We":[36],"introduce":[37],"a":[38,111,117,129],"novel":[39],"method":[40],"for":[41],"learning":[44,73],"that":[45],"incorporates":[46],"two":[47],"key":[48],"innovations:":[49],"probabilistic":[50],"content":[51],"masking,":[52],"encourages":[54],"model":[56,78,131],"to":[57,128],"focus":[58],"stylistically":[60],"indicative":[61],"words":[62],"rather":[63],"than":[64],"contentspecific":[65],"words,":[66],"and":[67,89,124],"language-aware":[68],"batching,":[69],"improves":[71],"contrastive":[72],"by":[74],"reducing":[75],"cross-lingual":[76,123],"interference.Our":[77],"is":[79],"trained":[80,132],"over":[82],"4.5":[83],"million":[84],"authors":[85],"across":[86],"36":[87],"languages":[88],"13":[90],"domains.It":[91],"consistently":[92],"outperforms":[93],"baselines":[95],"21":[97],"out":[98],"22":[100],"non-English":[101],"languages,":[102],"achieving":[103],"average":[105],"Recall@8":[106],"improvement":[107],"4.85%,":[109],"with":[110],"maximum":[112],"gain":[113],"15.91%":[115],"single":[118],"language.Furthermore,":[119],"it":[120],"exhibits":[121],"stronger":[122],"cross-domain":[125],"generalization":[126],"compared":[127],"solely":[133],"English.Our":[135],"analysis":[136],"confirms":[137],"effectiveness":[139],"both":[141],"proposed":[142],"techniques,":[143],"highlighting":[144],"their":[145],"critical":[146],"roles":[147],"model's":[150],"improved":[151],"performance.":[152]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-11-08T00:00:00"}