Dictionary-based Debiasing of Pre-trained Word Embeddings

Masahiro Kaneko, Danushka Bollegala


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 embedding, (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.
Anthology ID:
2021.eacl-main.16
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
212–223
Language:
URL:
https://aclanthology.org/2021.eacl-main.16
DOI:
10.18653/v1/2021.eacl-main.16
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.16.pdf
Code
 kanekomasahiro/dict-debias
Data
WinoBias