MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation

TL;DR

MT-GenEval is a new benchmark dataset designed to evaluate gender accuracy in machine translation across eight languages, using realistic, gender-balanced, counterfactual data to address ethical and accuracy concerns.

Contribution

It introduces a novel, gender-balanced, counterfactual dataset for evaluating gender accuracy in machine translation from English into eight languages.

Findings

Provides realistic, gender-balanced, counterfactual data

Addresses gender accuracy in multi-sentence translation

Supports evaluation of ethical implications in MT

Abstract

As generic machine translation (MT) quality has improved, the need for targeted benchmarks that explore fine-grained aspects of quality has increased. In particular, gender accuracy in translation can have implications in terms of output fluency, translation accuracy, and ethics. In this paper, we introduce MT-GenEval, a benchmark for evaluating gender accuracy in translation from English into eight widely-spoken languages. MT-GenEval complements existing benchmarks by providing realistic, gender-balanced, counterfactual data in eight language pairs where the gender of individuals is unambiguous in the input segment, including multi-sentence segments requiring inter-sentential gender agreement. Our data and code is publicly available under a CC BY SA 3.0 license.