{"id":"https://openalex.org/W4396600241","doi":"https://doi.org/10.1145/3630106.3658925","title":"Tackling Language Modelling Bias in Support of Linguistic Diversity","display_name":"Tackling Language Modelling Bias in Support of Linguistic Diversity","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4396600241","doi":"https://doi.org/10.1145/3630106.3658925"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658925","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075478426","display_name":"G\u00e1bor Bella","orcid":"https://orcid.org/0000-0002-3868-1740"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"G\u00e1bor Bella","raw_affiliation_strings":["Lab-STICC, CNRS UMR 6285, IMT Atlantique, France"],"affiliations":[{"raw_affiliation_string":"Lab-STICC, CNRS UMR 6285, IMT Atlantique, France","institution_ids":["https://openalex.org/I4210127572","https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057959142","display_name":"Paula Helm","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paula Helm","raw_affiliation_strings":["Faculty of Humanities, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Faculty of Humanities, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074914419","display_name":"Gertraud Koch","orcid":"https://orcid.org/0000-0002-2457-3335"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gertraud Koch","raw_affiliation_strings":["Institute of Anthropological Studies on Culture and History, University of Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Anthropological Studies on Culture and History, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001227032","display_name":"Fausto Giunchiglia","orcid":"https://orcid.org/0000-0002-5903-6150"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fausto Giunchiglia","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075478426"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702","https://openalex.org/I4210127572"],"apc_list":null,"apc_paid":null,"fwci":6.2715,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.96562005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9807000160217285,"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":0.9790999889373779,"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/computer-science","display_name":"Computer science","score":0.7509956359863281},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6057254672050476},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.529274582862854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5273714065551758},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5222538113594055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47897815704345703},{"id":"https://openalex.org/keywords/corollary","display_name":"Corollary","score":0.4784012734889984},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4692912995815277},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46705377101898193},{"id":"https://openalex.org/keywords/language-technology","display_name":"Language technology","score":0.45288845896720886},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4277627170085907},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.21753144264221191},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.20747756958007812},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.18821004033088684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509956359863281},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6057254672050476},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.529274582862854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5273714065551758},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5222538113594055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47897815704345703},{"id":"https://openalex.org/C2780012671","wikidata":"https://www.wikidata.org/wiki/Q1343870","display_name":"Corollary","level":2,"score":0.4784012734889984},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4692912995815277},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46705377101898193},{"id":"https://openalex.org/C14919245","wikidata":"https://www.wikidata.org/wiki/Q1976109","display_name":"Language technology","level":4,"score":0.45288845896720886},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4277627170085907},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.21753144264221191},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.20747756958007812},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.18821004033088684},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3630106.3658925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658925","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/5abf7f0d-a752-4a8a-9d61-6eff48c08160","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/tackling-language-modelling-bias-in-support-of-linguistic-diversity(5abf7f0d-a752-4a8a-9d61-6eff48c08160).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bella, G, Helm, P, Koch, G & Giunchiglia, F 2024, Tackling Language Modelling Bias in Support of Linguistic Diversity. in ACM FAccT '24 : Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency : June 3rd-6th 2024, Rio de Janeiro, Brazil. New York, pp. 562-572, 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024, Rio de Janeiro, Brazil, 3/06/24. https://doi.org/10.1145/3630106.3658925","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-04564896v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04564896","pdf_url":"https://hal.science/hal-04564896/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency, ACM, Jun 2024, Rio de Janeiro, Brazil. pp.562-572, &#x27E8;10.1145/3630106.3658925&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:iris.unitn.it:11572/464121","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/464121","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658925","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321008","display_name":"Universiteit van Amsterdam","ror":"https://ror.org/04dkp9463"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396600241.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1964045210","https://openalex.org/W1982341063","https://openalex.org/W2006447892","https://openalex.org/W2007619812","https://openalex.org/W2038721957","https://openalex.org/W2130645129","https://openalex.org/W2148587638","https://openalex.org/W2283323915","https://openalex.org/W2318516124","https://openalex.org/W2615499310","https://openalex.org/W2733628661","https://openalex.org/W2740960106","https://openalex.org/W2759083144","https://openalex.org/W2795621450","https://openalex.org/W3037831233","https://openalex.org/W3092614733","https://openalex.org/W3146083582","https://openalex.org/W3157526739","https://openalex.org/W4285161181","https://openalex.org/W4285664076","https://openalex.org/W4287646283","https://openalex.org/W4288096731","https://openalex.org/W4391282676"],"related_works":["https://openalex.org/W2376029318","https://openalex.org/W2388301251","https://openalex.org/W2013770701","https://openalex.org/W3013941779","https://openalex.org/W1998659141","https://openalex.org/W3195376785","https://openalex.org/W2951185269","https://openalex.org/W2319937810","https://openalex.org/W2370435933","https://openalex.org/W2947625790"],"abstract_inverted_index":{"Current":[0],"AI-based":[1],"language":[2,54,58,77,111,125],"technologies\u2014language":[3],"models,":[4],"machine":[5],"translation":[6],"systems,":[7],"multilingual":[8,57],"dictionaries":[9],"and":[10,68,103,135],"corpora\u2014are":[11],"known":[12],"to":[13,31,35,44,47],"focus":[14],"on":[15,138],"the":[16,26,108],"world\u2019s":[17],"2\u20133%":[18],"most":[19],"widely":[20],"spoken":[21],"languages.":[22,74],"Research":[23],"efforts":[24],"of":[25,40,110],"past":[27],"decade":[28],"have":[29],"attempted":[30],"expand":[32],"this":[33],"coverage":[34],"\u2018under-resourced":[36],"languages.\u2019":[37],"The":[38],"goal":[39],"our":[41],"paper":[42],"is":[43],"bring":[45],"attention":[46],"a":[48,63],"corollary":[49],"phenomenon":[50],"that":[51,90,106,121],"we":[52,117],"call":[53],"modelling":[55,78,126],"bias:":[56],"processing":[59],"systems":[60],"often":[61],"exhibit":[62],"hardwired,":[64],"yet":[65],"usually":[66],"involuntary":[67],"hidden":[69],"representational":[70],"preference":[71],"towards":[72,114],"certain":[73],"We":[75,88],"define":[76],"bias":[79,91,127],"as":[80],"uneven":[81],"per-language":[82],"performance":[83],"under":[84],"similar":[85],"test":[86],"conditions.":[87],"show":[89],"stems":[92],"not":[93],"only":[94],"from":[95,99],"technology":[96,133],"but":[97],"also":[98],"ethically":[100],"problematic":[101],"research":[102],"development":[104],"methodologies":[105],"disregard":[107],"needs":[109],"communities.":[112,144],"Moving":[113],"diversity-aware":[115],"alternatives,":[116],"present":[118],"an":[119,139],"initiative":[120],"aims":[122],"at":[123],"reducing":[124],"within":[128],"lexical":[129],"resources":[130],"through":[131],"both":[132],"design":[134],"methodology,":[136],"based":[137],"eye-level":[140],"collaboration":[141],"with":[142],"local":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
