Zero-pronoun Data Augmentation for Japanese-to-English Translation

TL;DR

This paper introduces a data augmentation technique that enhances Japanese-to-English translation by improving the model's ability to handle zero pronouns using local context cues, leading to better translation accuracy.

Contribution

The study proposes a novel data augmentation method that provides additional training signals for zero pronoun translation in Japanese-English machine translation.

Findings

Significant improvement in zero pronoun translation accuracy

Effective use of local context for pronoun inference

Enhanced translation performance in conversational domain

Abstract

For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often needs discourse context, in some cases, the local context within a sentence gives clues to the inference of the zero pronoun. In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. We show that the proposed method significantly improves the accuracy of zero pronoun translation with machine translation experiments in the conversational domain.