{"id":"https://openalex.org/W4287887516","doi":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","title":"Incorporating Subjectivity into Gendered Ambiguous Pronoun (GAP) Resolution using Style Transfer","display_name":"Incorporating Subjectivity into Gendered Ambiguous Pronoun (GAP) Resolution using Style Transfer","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4287887516","doi":"https://doi.org/10.18653/v1/2022.gebnlp-1.28"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.gebnlp-1.28","doi":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","pdf_url":"https://aclanthology.org/2022.gebnlp-1.28.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.gebnlp-1.28.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042969887","display_name":"Kartikey Pant","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartikey Pant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038587662","display_name":"Tanvi Dadu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanvi Dadu","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":0.3143,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4979102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4652999937534332,"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":0.4652999937534332,"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/T13173","display_name":"Gender Studies in Language","score":0.11540000140666962,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"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/T10028","display_name":"Topic Modeling","score":0.09920000284910202,"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/coreference-resolution","display_name":"coreference resolution","score":0.8930000066757202},{"id":"https://openalex.org/keywords/gender-bias","display_name":"gender bias","score":0.6830000281333923},{"id":"https://openalex.org/keywords/subjectivity","display_name":"subjectivity","score":0.8640000224113464},{"id":"https://openalex.org/keywords/style-transfer","display_name":"style transfer","score":0.8119999766349792},{"id":"https://openalex.org/keywords/content-preservation","display_name":"content preservation","score":0.8040000200271606},{"id":"https://openalex.org/keywords/bert-based-models","display_name":"BERT-based models","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123160004615784},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.7864392995834351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511720418930054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5969586968421936},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5302056074142456},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5141173005104065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5053744912147522},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4691646993160248},{"id":"https://openalex.org/C202889954","wikidata":"https://www.wikidata.org/wiki/Q1139554","display_name":"Subjectivity","level":2,"score":0.4582897424697876},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.45369887351989746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34750059247016907},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14676901698112488},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.gebnlp-1.28","doi":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","pdf_url":"https://aclanthology.org/2022.gebnlp-1.28.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.gebnlp-1.28","doi":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.gebnlp-1.28","pdf_url":"https://aclanthology.org/2022.gebnlp-1.28.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6025999784469604,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"},{"score":0.5676000118255615,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287887516.pdf","grobid_xml":"https://content.openalex.org/works/W4287887516.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2115553938","https://openalex.org/W2133341045","https://openalex.org/W2133564696","https://openalex.org/W2145451908","https://openalex.org/W2155069789","https://openalex.org/W2168776871","https://openalex.org/W2574872930","https://openalex.org/W2606974598","https://openalex.org/W2626778328","https://openalex.org/W2735642330","https://openalex.org/W2769358515","https://openalex.org/W2798280648","https://openalex.org/W2798651744","https://openalex.org/W2888167352","https://openalex.org/W2893425640","https://openalex.org/W2896331720","https://openalex.org/W2919290281","https://openalex.org/W2946068894","https://openalex.org/W2950018712","https://openalex.org/W2963526187","https://openalex.org/W2963667126","https://openalex.org/W2964165364","https://openalex.org/W2969646439","https://openalex.org/W2972771542","https://openalex.org/W3006260012","https://openalex.org/W3015941312","https://openalex.org/W3033129824"],"related_works":["https://openalex.org/W3103178954","https://openalex.org/W2972708930","https://openalex.org/W2973047719","https://openalex.org/W4386566571","https://openalex.org/W2947720606","https://openalex.org/W2920114910","https://openalex.org/W2973174663","https://openalex.org/W2796868841","https://openalex.org/W3197577761","https://openalex.org/W2949044118"],"abstract_inverted_index":{"The":[0],"GAP":[1,60,130],"dataset":[2,7,45,61],"is":[3,20],"a":[4,42,86,135],"Wikipedia-based":[5],"evaluation":[6,44],"for":[8,32,46],"gender":[9,47,144],"bias":[10,48],"detection":[11],"in":[12,22,49],"coreference":[13,50],"resolution,":[14,51],"containing":[15],"mostly":[16],"objective":[17,36,76],"sentences.Since":[18],"subjectivity":[19],"ubiquitous":[21],"our":[23],"daily":[24],"texts,":[25],"it":[26],"becomes":[27],"necessary":[28],"to":[29,70,100],"evaluate":[30],"models":[31],"both":[33,129],"subjective":[34,64,83],"and":[35,78,97,110,117,131,138,143],"instances.In":[37],"this":[38,72],"work,":[39],"we":[40,74,89,107,127],"present":[41],"new":[43],"GAP-Subjective,":[52],"which":[53],"increases":[54],"the":[55,58,67,91,102,105,114,120],"coverage":[56],"of":[57,104,113,124],"original":[59],"by":[62],"including":[63],"sentences.We":[65],"outline":[66,90],"methodology":[68],"used":[69],"create":[71],"dataset.Firstly,":[73],"detect":[75],"sentences":[77,122],"transfer":[79,116],"them":[80],"into":[81],"their":[82],"variants":[84],"using":[85,134],"sequenceto-sequence":[87],"model.Secondly,":[88],"thresholding":[92],"techniques":[93],"based":[94],"on":[95],"fluency":[96],"content":[98],"preservation":[99],"maintain":[101],"quality":[103],"sentences.Thirdly,":[106],"perform":[108],"automated":[109],"human-based":[111],"analysis":[112],"style":[115],"infer":[118],"that":[119],"transferred":[121],"are":[123],"high":[125],"quality.Finally,":[126],"benchmark":[128],"GAP-Subjective":[132],"datasets":[133],"BERTbased":[136],"model":[137],"analyze":[139],"its":[140],"predictive":[141],"performance":[142],"bias.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2022-07-26T00:00:00"}