Learning Gender-Neutral Word Embeddings
This addresses bias in NLP applications for users affected by stereotypical outputs, though it is an incremental improvement on existing embedding methods.
The paper tackled the problem of gender stereotypes in word embeddings by proposing a novel training procedure to learn gender-neutral embeddings, resulting in GN-GloVe, which isolates gender information without compromising functionality as shown in experiments.
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propose a novel training procedure for learning gender-neutral word embeddings. Our approach aims to preserve gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence. Based on the proposed method, we generate a Gender-Neutral variant of GloVe (GN-GloVe). Quantitative and qualitative experiments demonstrate that GN-GloVe successfully isolates gender information without sacrificing the functionality of the embedding model.