Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns

arXiv:2405.00134v1 Announce Type: new
Abstract: Gender-neutral pronouns are increasingly being introduced across Western languages. Recent evaluations have however demonstrated that English NLP systems are unable to correctly process gender-neutral pronouns, with the risk of erasing and misgendering non-binary individuals. This paper examines a Dutch coreference resolution system's performance on gender-neutral pronouns, specifically hen and die. In Dutch, these pronouns were only introduced in 2016, compared to the longstanding existence of singular they in English. We additionally compare two debiasing techniques …

abstract arxiv binary cs.ai cs.cl english gender however languages nlp nlp systems paper performance process resolution risk s performance systems type