Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It

TL;DR

This paper investigates methods to improve neural machine translation's handling of gender coreference by incorporating explicit word-level gender tags, demonstrating that targeted data and tagging strategies enhance translation accuracy for gendered language pairs.

Contribution

It introduces explicit word-level gender inflection tags into NMT and evaluates their effectiveness, proposing coreference-aware data augmentation and gender-neutral translation extensions.

Findings

Simple gender-tagging approaches over-generalize to multiple entities.

Tagged coreference data improves gender translation accuracy.

Extensions enable translation of gender-neutral English entities.

Abstract

Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek to control gender inflection in the target language by explicitly or implicitly adding a gender feature to the source sentence, usually at the sentence level. In this paper we propose schemes for incorporating explicit word-level gender inflection tags into NMT. We explore the potential of this gender-inflection controlled translation when the gender feature can be determined from a human reference, or when a test sentence can be automatically gender-tagged, assessing on English-to-Spanish and English-to-German translation. We find that simple existing approaches can over-generalize a gender-feature to multiple entities in a sentence, and suggest effective alternatives in the form of tagged coreference adaptation data. We also propose an extension to assess translations of gender-neutral entities from English given a corresponding linguistic convention, such as a non-binary inflection, in the target language.