{"id":"https://openalex.org/W2949969209","doi":"https://doi.org/10.18653/v1/p19-1160","title":"Gender-preserving Debiasing for Pre-trained Word Embeddings","display_name":"Gender-preserving Debiasing for Pre-trained Word Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949969209","doi":"https://doi.org/10.18653/v1/p19-1160","mag":"2949969209"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1160","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1160","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005531754","display_name":"Masahiro Kaneko","orcid":"https://orcid.org/0000-0002-5117-5447"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Kaneko","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073503574","display_name":"Danushka Bollegala","orcid":"https://orcid.org/0000-0003-4476-7003"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danushka Bollegala","raw_affiliation_strings":["University of Liverpool, UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005531754"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":9.837,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.98419207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1641","last_page":"1650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9922000169754028,"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/debiasing","display_name":"Debiasing","score":0.976338267326355},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7816483378410339},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7674846649169922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.663045346736908},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6321337819099426},{"id":"https://openalex.org/keywords/gender-bias","display_name":"Gender bias","score":0.5447372794151306},{"id":"https://openalex.org/keywords/coreference","display_name":"Coreference","score":0.5415563583374023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5368978977203369},{"id":"https://openalex.org/keywords/neutrality","display_name":"Neutrality","score":0.4959612786769867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45752039551734924},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34652793407440186},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.2177831530570984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15599524974822998},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.0611075758934021}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.976338267326355},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7816483378410339},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7674846649169922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.663045346736908},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6321337819099426},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.5447372794151306},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.5415563583374023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368978977203369},{"id":"https://openalex.org/C2779581858","wikidata":"https://www.wikidata.org/wiki/Q9049677","display_name":"Neutrality","level":2,"score":0.4959612786769867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45752039551734924},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34652793407440186},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2177831530570984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15599524974822998},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0611075758934021},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1160","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1160","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/5","score":0.4300000071525574,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W1522301498","https://openalex.org/W1854884267","https://openalex.org/W2067438047","https://openalex.org/W2080100102","https://openalex.org/W2098801107","https://openalex.org/W2118090838","https://openalex.org/W2137591261","https://openalex.org/W2137735870","https://openalex.org/W2140534852","https://openalex.org/W2141599568","https://openalex.org/W2142625445","https://openalex.org/W2153579005","https://openalex.org/W2157928966","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2483215953","https://openalex.org/W2758729290","https://openalex.org/W2888161220","https://openalex.org/W2889624842","https://openalex.org/W2891525068","https://openalex.org/W2893425640","https://openalex.org/W2896457183","https://openalex.org/W2904233591","https://openalex.org/W2949157927","https://openalex.org/W2950018712","https://openalex.org/W2962739339","https://openalex.org/W2962869292","https://openalex.org/W2963446520","https://openalex.org/W2963457723","https://openalex.org/W2963526187","https://openalex.org/W2963825865","https://openalex.org/W2963879260","https://openalex.org/W2964121744","https://openalex.org/W3099361686","https://openalex.org/W4231165370","https://openalex.org/W4231284028","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W3037697022","https://openalex.org/W3171711591","https://openalex.org/W1995736631","https://openalex.org/W3186506180","https://openalex.org/W2921633540","https://openalex.org/W3034021819","https://openalex.org/W4286411893","https://openalex.org/W3083213769","https://openalex.org/W2949969209","https://openalex.org/W2947283491"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,128,138],"learnt":[2],"from":[3,56,108],"massive":[4],"text":[5],"collections":[6],"have":[7],"demonstrated":[8],"significant":[9],"levels":[10],"of":[11,65],"discriminative":[12,53],"biases":[13,55,107],"such":[14],"as":[15,36],"gender,":[16],"racial":[17],"or":[18],"ethnic":[19],"biases,":[20],"which":[21,72],"in":[22,91,100],"turn":[23],"bias":[24],"the":[25,74,88,98,106],"down-stream":[26],"NLP":[27],"applications":[28],"that":[29,45,85,120],"use":[30],"those":[31],"word":[32,58,127,137],"embeddings.":[33,59],"Taking":[34],"gender-bias":[35],"a":[37,42,82],"working":[38],"example,":[39],"we":[40,61],"propose":[41,81],"debiasing":[43,83,136],"method":[44,84,123],"preserves":[46,87,97],"non-discriminative":[47,143],"gender-related":[48,89,141],"information,":[49],"while":[50,139],"removing":[51],"stereotypical":[52,109],"gender":[54,77],"pre-trained":[57,126],"Specifically,":[60],"consider":[62],"four":[63],"types":[64],"information:":[66],"feminine,":[67],"masculine,":[68],"gender-neutral":[69,101],"and":[70,80,93,103],"stereotypical,":[71],"represent":[73],"relationship":[75],"between":[76],"vs.":[78],"bias,":[79],"(a)":[86],"information":[90],"feminine":[92],"masculine":[94],"words,":[95,102],"(b)":[96],"neutrality":[99],"(c)":[104],"removes":[105],"words.":[110],"Experimental":[111],"results":[112],"on":[113],"several":[114],"previously":[115],"proposed":[116,122,134],"benchmark":[117],"datasets":[118],"show":[119],"our":[121],"can":[124],"debias":[125],"better":[129],"than":[130],"existing":[131],"SoTA":[132],"methods":[133],"for":[135],"preserving":[140],"but":[142],"information.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}