Evaluating Gender Bias in Pre-trained Filipino FastText Embeddings

• Main Authors: Gamboa, Lance Calvin, Estuar, Ma. Regina Justina
• Format: text
• Published: Archīum Ateneo 2023
• Subjects: FastText; Filipino; gender bias; principal component analysis; word embedding; Word Embedding Association Test; Computer Engineering; Electrical and Computer Engineering; Engineering
• Online Access: https://archium.ateneo.edu/discs-faculty-pubs/379; https://doi.org/10.1109/ITIKD56332.2023.10100022
• Institution: Ateneo De Manila University

Past studies show that word embeddings can learn gender biases introduced by human agents into the textual corpora used to train these models. However, it has also been shown that some non-English embeddings may actually not capture such biases in their word representations. This study, therefore, a...