Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving

1 code implementation • 9 Dec 2021 • Lei Ding, Dengdeng Yu, Jinhan Xie, Wenxing Guo, Shenggang Hu, Meichen Liu, Linglong Kong, Hongsheng Dai, Yanchun Bao, Bei Jiang

The proposed method allows us to construct and analyze the complex causal mechanisms facilitating gender information flow while retaining oracle semantic information within word embeddings.

Causal Inference Word Embeddings +1