Dictionary-based Debiasing of Pre-trained Word Embeddings

TL;DR

This paper introduces a dictionary-based method for debiasing pre-trained word embeddings that automatically learns constraints from dictionary definitions, effectively reducing biases without needing original training data or bias-specific word lists.

Contribution

It presents a novel debiasing approach that leverages dictionaries to automatically learn constraints, avoiding the need for predefined bias types or training resources.

Findings

Successfully removes biases from word embeddings

Preserves semantic information in embeddings

Outperforms existing debiasing methods on benchmarks

Abstract

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective and an unbiased manner. We propose a method for debiasing pre-trained word embeddings using dictionaries, without requiring access to the original training resources or any knowledge regarding the word embedding algorithms used. Unlike prior work, our proposed method does not require the types of biases to be pre-defined in the form of word lists, and learns the constraints that must be satisfied by unbiased word embeddings automatically from dictionary definitions of the words. Specifically, we learn an encoder to generate a debiased version of an input word embedding such that it (a) retains the semantics of the pre-trained word embeddings, (b) agrees with the unbiased definition of the word according to the dictionary, and (c) remains orthogonal to the vector space spanned by any biased basis vectors in the pre-trained word embedding space. Experimental results on standard benchmark datasets show that the proposed method can accurately remove unfair biases encoded in pre-trained word embeddings, while preserving useful semantics.