Mitigating Language-Dependent Ethnic Bias in BERT

09/13/2021
by   Jaimeen Ahn, et al.
15

BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this paper, we study ethnic bias and how it varies across languages by analyzing and mitigating ethnic bias in monolingual BERT for English, German, Spanish, Korean, Turkish, and Chinese. To observe and quantify ethnic bias, we develop a novel metric called Categorical Bias score. Then we propose two methods for mitigation; first using a multilingual model, and second using contextual word alignment of two monolingual models. We compare our proposed methods with monolingual BERT and show that these methods effectively alleviate the ethnic bias. Which of the two methods works better depends on the amount of NLP resources available for that language. We additionally experiment with Arabic and Greek to verify that our proposed methods work for a wider variety of languages.

READ FULL TEXT

page 5

page 8

page 17

research
10/27/2020

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias

Contextualized word embeddings have been replacing standard embeddings a...
research
11/25/2022

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages

Although large pre-trained language models have achieved great success i...
research
05/23/2023

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

Are language models culturally biased? It is important that language mod...
research
06/15/2023

Voting Booklet Bias: Stance Detection in Swiss Federal Communication

In this study, we use recent stance detection methods to study the stanc...
research
09/13/2021

Evaluating Transferability of BERT Models on Uralic Languages

Transformer-based language models such as BERT have outperformed previou...
research
07/14/2023

How Different Is Stereotypical Bias Across Languages?

Recent studies have demonstrated how to assess the stereotypical bias in...
research
11/27/2019

Sideways Transliteration: How to Transliterate Multicultural Person Names?

In a global setting, texts contain transliterated names from many cultur...

Please sign up or login with your details

Forgot password? Click here to reset