GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation

TL;DR

This paper presents GOSt-MT, a knowledge graph combining real-world gender statistics and textual data to analyze and address occupation-related gender biases in machine translation across multiple languages.

Contribution

Introduction of GOSt-MT, a comprehensive knowledge graph that links labour gender data with MT training corpora to study and mitigate gender biases in translation systems.

Findings

Identifies persistent gender stereotypes in MT outputs.

Highlights differences in gender bias across English, French, and Greek.

Provides a framework for bias analysis and intervention in MT.

Abstract

Gender bias in machine translation (MT) systems poses significant challenges that often result in the reinforcement of harmful stereotypes. Especially in the labour domain where frequently occupations are inaccurately associated with specific genders, such biases perpetuate traditional gender stereotypes with a significant impact on society. Addressing these issues is crucial for ensuring equitable and accurate MT systems. This paper introduces a novel approach to studying occupation-related gender bias through the creation of the GOSt-MT (Gender and Occupation Statistics for Machine Translation) Knowledge Graph. GOSt-MT integrates comprehensive gender statistics from real-world labour data and textual corpora used in MT training. This Knowledge Graph allows for a detailed analysis of gender bias across English, French, and Greek, facilitating the identification of persistent stereotypes and areas requiring intervention. By providing a structured framework for understanding how occupations are gendered in both labour markets and MT systems, GOSt-MT contributes to efforts aimed at making MT systems more equitable and reducing gender biases in automated translations.