Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation

TL;DR

This paper introduces a multi-task learning approach to improve dialogue machine translation by addressing pronoun dropping, punctuation dropping, and typos, using a new annotated dataset and achieving significant quality improvements.

Contribution

It proposes a joint learning method for dialogue translation that handles omission and typos, along with a new benchmark dataset for evaluation.

Findings

Translation quality improved by 3.2 BLEU points.

Recovery rate of omitted pronouns increased from 26.09% to 47.16%.

Introduces a new dataset for dialogue translation evaluation.

Abstract

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue corpus and summarize three major issues on dialogue translation, including pronoun dropping (\droppro), punctuation dropping (\droppun), and typos (\typo). In response to these challenges, we propose a joint learning method to identify omission and typo, and utilize context to translate dialogue utterances. To properly evaluate the performance, we propose a manually annotated dataset with 1,931 Chinese-English parallel utterances from 300 dialogues as a benchmark testbed for dialogue translation. Our experiments show that the proposed method improves translation quality by 3.2 BLEU over the baselines. It also elevates the recovery rate of omitted pronouns from 26.09% to 47.16%. We will publish the code and dataset publicly at https://github.com/rgwt123/DialogueMT.