CHI '242nd AuthorAI Ethics, Fairness & Accountability +1
STILE: Exploring and Debugging Social Biases in Pre-trained Text Representations
The recent success of Natural Language Processing (NLP) relies heavily on pre-trained text representations such as word embeddings. However, pre-trained text representations may exhibit social biases and stereotypes, e.g., disproportionately associating gender with occupations. Though prior work presented various bias…