Is there Gender bias and stereotype in Portuguese Word Embeddings?
arXiv:1810.04528v112 citations
Originality Synthesis-oriented
AI Analysis
This addresses potential fairness issues in NLP applications for Portuguese speakers, but it is incremental as it extends similar analyses from other languages to Portuguese.
The paper analyzed gender bias and stereotypes in Portuguese word embeddings, specifically focusing on professions, and identified the presence of such biases in the embeddings.
In this work, we propose an analysis of the presence of gender bias associated with professions in Portuguese word embeddings. The objective of this work is to study gender implications related to stereotyped professions for women and men in the context of the Portuguese language.