{"id":"https://openalex.org/W6929197019","doi":"https://doi.org/10.48550/arxiv.2502.19104","title":"Are All Spanish Doctors Male? Evaluating Gender Bias in German Machine Translation","display_name":"Are All Spanish Doctors Male? Evaluating Gender Bias in German Machine Translation","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W6929197019","doi":"https://doi.org/10.48550/arxiv.2502.19104"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.19104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19104","pdf_url":"https://arxiv.org/pdf/2502.19104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.19104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kappl, Michelle","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kappl, Michelle","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.47749999165534973,"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":0.47749999165534973,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.3628000020980835,"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/T13173","display_name":"Gender Studies in Language","score":0.04809999838471413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gender-bias","display_name":"gender bias","score":0.7960000038146973},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/gender-underrepresentation","display_name":"gender underrepresentation","score":0.6549999713897705},{"id":"https://openalex.org/keywords/german-language","display_name":"German language","score":0.5569999814033508},{"id":"https://openalex.org/keywords/grammatical-gender","display_name":"grammatical gender","score":0.9760000109672546},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9200000166893005},{"id":"https://openalex.org/keywords/labor-statistics","display_name":"labor statistics","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8913000226020813},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.6219000220298767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5619999766349792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5346999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41659998893737793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C192420165","wikidata":"https://www.wikidata.org/wiki/Q162378","display_name":"Grammatical gender","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38499999046325684},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.259799987077713},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.19104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19104","pdf_url":"https://arxiv.org/pdf/2502.19104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2502.19104","doi":"https://doi.org/10.48550/arxiv.2502.19104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.19104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.19104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19104","pdf_url":"https://arxiv.org/pdf/2502.19104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2947599143","https://openalex.org/W3092827761","https://openalex.org/W4416035277","https://openalex.org/W3185106120","https://openalex.org/W7111909063","https://openalex.org/W7213924617","https://openalex.org/W4402669943","https://openalex.org/W7066591614","https://openalex.org/W4391976396","https://openalex.org/W7134817645"],"abstract_inverted_index":{"We":[0,68],"present":[1],"WinoMTDE,":[2],"a":[3,38,70,80],"new":[4],"gender":[5],"bias":[6,88],"evaluation":[7,27,72,101],"test":[8],"set":[9],"designed":[10],"to":[11,36,55],"assess":[12],"occupational":[13],"stereotyping":[14],"and":[15,79,100],"underrepresentation":[16],"in":[17,53,89],"German":[18,48,65],"machine":[19],"translation":[20],"(MT)":[21],"systems.":[22,97],"Building":[23],"on":[24],"the":[25,34,93],"automatic":[26],"method":[28],"introduced":[29],"by":[30],"arXiv:1906.00591v1,":[31],"we":[32],"extend":[33],"approach":[35],"German,":[37],"language":[39,82],"with":[40,92],"grammatical":[41],"gender.":[42],"The":[43,98],"WinoMTDE":[44],"dataset":[45,99],"comprises":[46],"288":[47],"sentences":[49],"that":[50],"are":[51,103],"balanced":[52],"regard":[54],"gender,":[56],"as":[57,59],"well":[58],"stereotype,":[60],"which":[61],"was":[62],"annotated":[63],"using":[64],"labor":[66],"statistics.":[67],"conduct":[69],"large-scale":[71],"of":[73],"five":[74],"widely":[75],"used":[76],"MT":[77],"systems":[78],"large":[81],"model.":[83],"Our":[84],"results":[85],"reveal":[86],"persistent":[87],"most":[90],"models,":[91],"LLM":[94],"outperforming":[95],"traditional":[96],"code":[102],"publicly":[104],"available":[105],"under":[106],"https://github.com/michellekappl/mt_gender_german.":[107]},"counts_by_year":[],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2025-10-10T00:00:00"}