Scheduled Multi-task Learning for Neural Chat Translation

The goal of the Neural Chat Translation (NCT) is to translate conversational text into different languages. Existing methods mainly focus on modeling the bilingual dialogue characteristics (e.g., coherence) to improve chat translation via multi-task learning on smallscale chat translation data. Although the NCT models have achieved impressive success, it is still far from satisfactory due to insufficient chat translation data and simple joint training manners. To address the above issues, we propose a scheduled multi-task learning framework for NCT. Specifically, we devise a three-stage training framework to incorporate the large-scale in-domain chat translation data into training by adding a second pre-training stage between the original pre-training and fine-tuning stages. Further, we investigate where and how to schedule the dialoguerelated auxiliary tasks in multiple training stages to effectively enhance the main chat translation task. Extensive experiments on four language directions (English↔Chinese and English↔German) demonstrate the effectiveness of the proposed approach. Additionally, we have made the large-scale indomain paired bilingual dialogue dataset publicly available for the research community. 1