Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
In this paper, we study the bias in named entity recognition (NER) models—specifically, the difference in the ability to recognize male and female names as PERSON entity types. We evaluate NER models on a dataset containing 139 years of U.S. census baby names and find that relatively more female names, as opposed to male names, are not recognized as PERSON e- doi
- 10.1145/3372923.3404804
- name
- Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
- pages
- 2
- acm_url
- https://dl.acm.org/doi/10.1145/3372923.3404804
- authors
- Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan
- doi_url
- https://doi.org/10.1145/3372923.3404804
- license
- restricted
- summary
- In this paper, we study the bias in named entity recognition (NER) models—specifically, the difference in the ability to recognize male and female names as PERSON entity types. We evaluate NER models on a dataset containing 139 years of U.S. census baby names and find that relatively more female names, as opposed to male names, are not recognized as PERSON e
- keywords
- Algorithmic Fairness; Natural Language Processing; Named Entity Recognition; Evaluation
- source_pdf
- HT-2020_51-35_3372923/3372923.3404804.pdf
- import_kind
- full_text
- open_access
- false
- ccs_concepts
- • Computing methodologies →Artificial intelligence; Artificial intelligence; Natural language processing; Information extraction;
- displayAuthor
- Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan
- source_attribution
- Formatting converted from the ACM version of record under supplied ACM publication authorization.
Powered by Seed HypermediaOpen App