{"id":"https://openalex.org/W2798911413","doi":"https://doi.org/10.18653/v1/p18-2061","title":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction","display_name":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798911413","doi":"https://doi.org/10.18653/v1/p18-2061","mag":"2798911413"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2061","pdf_url":"https://www.aclweb.org/anthology/P18-2061.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-2061.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Rob van der Goot","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021557805","display_name":"Nikola Ljube\u0161i\u0107","orcid":"https://orcid.org/0000-0001-7169-9152"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Nikola Ljube\u0161i\u0107","raw_affiliation_strings":["Department of Knowledge Technologies, Jozef Stefan Institute, Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Department of Knowledge Technologies, Jozef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008904446","display_name":"Ian Matroos","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ian Matroos","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040564747","display_name":"Malvina Nissim","orcid":"https://orcid.org/0000-0001-5289-0971"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Malvina Nissim","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]},{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["DK","NL"],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, The Netherlands","IT University of Copenhagen, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039811894"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":5.2399,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96316784,"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":"383","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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":0.9846000075340271,"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":0.7964209914207458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6156936883926392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957502722740173},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5053597092628479},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.47061970829963684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964209914207458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6156936883926392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957502722740173},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5053597092628479},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.47061970829963684},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-2061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2061","pdf_url":"https://www.aclweb.org/anthology/P18-2061.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2061","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2061","pdf_url":"https://www.aclweb.org/anthology/P18-2061.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798911413.pdf","grobid_xml":"https://content.openalex.org/works/W2798911413.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W9292421","https://openalex.org/W50479354","https://openalex.org/W108437174","https://openalex.org/W1879024793","https://openalex.org/W2017729405","https://openalex.org/W2025403586","https://openalex.org/W2043500582","https://openalex.org/W2110302976","https://openalex.org/W2119595472","https://openalex.org/W2140907953","https://openalex.org/W2153890685","https://openalex.org/W2154819126","https://openalex.org/W2163688055","https://openalex.org/W2166434810","https://openalex.org/W2250238316","https://openalex.org/W2250969425","https://openalex.org/W2468547970","https://openalex.org/W2572403455","https://openalex.org/W2575864632","https://openalex.org/W2580038684","https://openalex.org/W2588986918","https://openalex.org/W2594021297","https://openalex.org/W2626534681","https://openalex.org/W2734855474","https://openalex.org/W2740994861","https://openalex.org/W2749516820","https://openalex.org/W2752530998","https://openalex.org/W2758820997","https://openalex.org/W2774523402","https://openalex.org/W2952190837","https://openalex.org/W2952732929","https://openalex.org/W2964090065","https://openalex.org/W2997591727","https://openalex.org/W3098567718","https://openalex.org/W4393675269"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Gender":[0],"prediction":[1],"has":[2],"typically":[3],"focused":[4],"on":[5,67],"lexical":[6,42,96],"and":[7,20,91],"social":[8],"network":[9],"features,":[10],"yielding":[11],"good":[12],"performance,":[13],"but":[14,29],"making":[15],"systems":[16],"highly":[17],"language-,":[18],"topic-,":[19],"platformdependent.":[21],"Cross-lingual":[22],"embeddings":[23],"circumvent":[24],"some":[25],"of":[26,70,87],"these":[27],"limitations,":[28],"capture":[30],"gender-specific":[31],"style":[32],"less.":[33],"We":[34,77],"propose":[35],"an":[36],"alternative:":[37],"bleaching":[38],"text,":[39],"i.e.,":[40],"transforming":[41],"strings":[43],"into":[44],"more":[45],"abstract":[46],"features.":[47],"This":[48],"study":[49,66],"provides":[50],"evidence":[51],"that":[52,79,86],"such":[53],"features":[54],"allow":[55],"for":[56],"better":[57,94],"transfer":[58],"across":[59],"languages.":[60],"Moreover,":[61],"we":[62],"present":[63],"a":[64],"first":[65],"the":[68],"ability":[69],"humans":[71],"to":[72,85],"perform":[73,93],"cross-lingual":[74],"gender":[75],"prediction.":[76],"find":[78],"human":[80],"predictive":[81],"power":[82],"proves":[83],"similar":[84],"our":[88],"bleached":[89],"models,":[90],"both":[92],"than":[95],"models.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}