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

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.

arXiv comment8 pages, 3 figures, 7 tables

References in corpus (6)

• Improving neural networks by preventing co-adaptation of feature detectors
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Multilingual Denoising Pre-training for Neural Machine Translation
• Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
• Translating Pro-Drop Languages with Reconstruction Models
• Findings of the WMT 2024 Shared Task on Chat Translation

Cited by in corpus (2)

• Towards Making the Most of Dialogue Characteristics for Neural Chat Translation
• Modeling Bilingual Conversational Characteristics for Neural Chat Translation