Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition

Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan

Abstract: 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 entities. The result of this analysis yields a new benchmark for gender bias evaluation in named entity recognition systems. The data and code for the application of this benchmark is publicly available for researchers to use.