How Gender Interacts with Political Values: A Case Study on Czech BERT Models

arXiv:2403.13514v1 Announce Type: new
Abstract: Neural language models, which reach state-of-the-art results on most natural language processing tasks, are trained on large text corpora that inevitably contain value-burdened content and often capture undesirable biases, which the models reflect. This case study focuses on the political biases of pre-trained encoders in Czech and compares them with a representative value survey. Because Czech is a gendered language, we also measure how the grammatical gender coincides with responses to men and women in …

abstract art arxiv bert bert models biases case case study cs.cl cs.cy czech gender language language models language processing natural natural language natural language processing political processing results state study tasks text type value values