Transcending the 'Male Code': Implicit Masculine Biases in NLP Contexts

Autor:	Seaborn, Katie, Chandra, Shruti, Fabre, Thibault
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Computers and Society Computer Science - Human-Computer Interaction Computer Science - Machine Learning
Zdroj:	In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 138, 1-19
Druh dokumentu:	Working Paper
DOI:	10.1145/3544548.3581017
Popis:	Critical scholarship has elevated the problem of gender bias in data sets used to train virtual assistants (VAs). Most work has focused on explicit biases in language, especially against women, girls, femme-identifying people, and genderqueer folk; implicit associations through word embeddings; and limited models of gender and masculinities, especially toxic masculinities, conflation of sex and gender, and a sex/gender binary framing of the masculine as diametric to the feminine. Yet, we must also interrogate how masculinities are "coded" into language and the assumption of "male" as the linguistic default: implicit masculine biases. To this end, we examined two natural language processing (NLP) data sets. We found that when gendered language was present, so were gender biases and especially masculine biases. Moreover, these biases related in nuanced ways to the NLP context. We offer a new dictionary called AVA that covers ambiguous associations between gendered language and the language of VAs. Comment: 19 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.12810 Zobrazit plný text záznamu View this record from Arxiv