Run Like a Girl! Sport-Related Gender Bias in Language and Vision

Gender bias in Language and Vision datasets models has the potential to perpetuate stereotypes and discrimination. We gender bias in two Language and Vision datasets. Consistent with prior work, we that both datasets underrepresent women, promotes their invisibilization. Moreover, we hypothesize and find that a bias affects human naming choices for people playing : speakers produce names indicating the (e.g. ‘tennis player’ or ‘surfer’) more often when it is a man or a boy participating in sport than when it is a woman or a girl, with average of 46% vs. 35% of sports-related for each gender. A computational model on these naming data reproduces the . We argue that both the data and the model in representational harm against women.