# Evaluating Gender Bias in Machine Translation

## TL;DR

This paper introduces a new benchmark and evaluation protocol to analyze gender bias in machine translation, revealing significant biases in popular systems across multiple languages.

## Contribution

It provides the first challenge set and automatic evaluation method for gender bias in MT, using coreference datasets and morphological analysis across eight languages.

## Key findings

- Popular MT systems exhibit significant gender bias.
- State-of-the-art models are also prone to gender bias.
- The dataset and code are publicly available.

## Abstract

We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of English sentences which cast participants into non-stereotypical gender roles (e.g., "The doctor asked the nurse to help her in the operation"). We devise an automatic gender bias evaluation method for eight target languages with grammatical gender, based on morphological analysis (e.g., the use of female inflection for the word "doctor"). Our analyses show that four popular industrial MT systems and two recent state-of-the-art academic MT models are significantly prone to gender-biased translation errors for all tested target languages. Our data and code are made publicly available.