Logo
User: Guest  Login
Authors:
Cimitan, Ana; Alves Pinto, Ana; Geierhos, Michaela 
Document type:
Konferenzbeitrag / Conference Paper 
Title:
Curation of Benchmark Templates for Measuring Gender Bias in Named Entity Recognition Models 
Collection editors:
Calzolari, Nicoletta; Kan, Min-Yen; Hoste, Veronique; Lenci, Alessandro; Sakti, Sakriani; Xue, Nianwen 
Title of conference publication:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) 
Conference title:
Joint International Conference on Computational Linguistics, Language Resources and Evaluation (2024, Turin) 
Venue:
Turin, Italien 
Year of conference:
2024 
Date of conference beginning:
20.05.2024 
Date of conference ending:
25.05.2024 
Publishing institution:
ELRA 
Year:
2024 
Pages from - to:
4238-4246 
Language:
Englisch 
Keywords:
BERT ; masked token prediction ; gender gap 
Abstract:
Named Entity Recognition (NER) constitutes a popular machine learning technique that empowers several natural language processing applications. As with other machine learning applications, NER models have been shown to be susceptible to gender bias. The latter is often assessed using benchmark datasets, which in turn are curated specifically for a given Natural Language Processing (NLP) task. In this work, we investigate the robustness of benchmark templates to detect gender bias and propose a n...    »
 
Department:
Fakultät für Informatik 
Institute:
INF 7 - Institut für Datensicherheit 
Chair:
Geierhos, Michaela 
Research Hub UniBw M:
CODE 
Open Access yes or no?:
Ja / Yes 
Type of OA license:
CC BY 4.0 Attribution 4.0 International License