Enhancing Interpretability using Human Similarity Judgements to Prune Word Embeddings

no code implementations • 16 Oct 2023 • Natalia Flechas Manrique, Wanqian Bao, Aurelie Herbelot, Uri Hasson

Focusing on word embeddings, we present a supervised-learning method that, for a given domain (e. g., sports, professions), identifies a subset of model features that strongly improve prediction of human similarity judgments.

Word Embeddings