{"id":"https://openalex.org/W7166801475","doi":"https://doi.org/10.18653/v1/2026.acl-long.342","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","display_name":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166801475","doi":"https://doi.org/10.18653/v1/2026.acl-long.342"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.342","pdf_url":"https://aclanthology.org/2026.acl-long.342.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.342.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041639724","display_name":"Negar Foroutan","orcid":"https://orcid.org/0000-0002-9640-897X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Negar Foroutan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139192844","display_name":"Clara Meister","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clara Meister","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042400301","display_name":"Debjit Paul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debjit Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139718594","display_name":"Joel Niklaus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joel Niklaus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139783954","display_name":"Sina Ahmadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sina Ahmadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139772678","display_name":"Antoine Bosselut","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Bosselut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139797414","display_name":"Rico Sennrich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rico Sennrich","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":0.79082881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7514","last_page":"7538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3476000130176544,"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":0.3476000130176544,"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":0.18889999389648438,"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":0.04439999908208847,"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/computational-linguistics","display_name":"Computational linguistics","score":0.3515999913215637},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.29019999504089355},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.2644999921321869},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.25119999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.342","pdf_url":"https://aclanthology.org/2026.acl-long.342.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.342","pdf_url":"https://aclanthology.org/2026.acl-long.342.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6554743051528931}],"awards":[{"id":"https://openalex.org/G3056497733","display_name":"Interfacing Neural and Symbolic Knowledge in Natural Language Systems","funder_award_id":"215390","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6575747830","display_name":"Multitask Learning with Multilingual Resources for Better Natural Language Understanding","funder_award_id":"213976","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8503654337","display_name":null,"funder_award_id":"PFFS-21-29","funder_id":"https://openalex.org/F4320327931","funder_display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320327931","display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","ror":"https://ror.org/05a2bhn71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166801475.pdf","grobid_xml":"https://content.openalex.org/works/W7166801475.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Negar":[0],"Foroutan,":[1],"Clara":[2],"Meister,":[3],"Debjit":[4],"Paul,":[5],"Joel":[6],"Niklaus,":[7],"Sina":[8],"Ahmadi,":[9],"Antoine":[10],"Bosselut,":[11],"Rico":[12],"Sennrich.":[13],"Proceedings":[14],"of":[15,20],"the":[16,21],"64th":[17],"Annual":[18],"Meeting":[19],"Association":[22],"for":[23],"Computational":[24],"Linguistics":[25],"(Volume":[26],"1:":[27],"Long":[28],"Papers).":[29],"2026.":[30]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
