Scheduled Multi-task Learning for Neural Chat Translation

TL;DR

This paper introduces a three-stage scheduled multi-task learning framework for neural chat translation, effectively leveraging large-scale in-domain data and auxiliary tasks to improve translation quality across multiple language pairs.

Contribution

It proposes a novel three-stage training approach with strategic scheduling of auxiliary tasks, enhancing chat translation performance and addressing data scarcity issues.

Findings

Outperforms existing methods in four language directions

Effectively incorporates large-scale in-domain data

Demonstrates the importance of task scheduling in training

Abstract

Neural Chat Translation (NCT) aims 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 small-scale 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 dialogue-related auxiliary tasks in multiple training stages to effectively enhance the main chat translation task. Extensive experiments in four language directions (English-Chinese and English-German) verify the effectiveness and superiority of the proposed approach. Additionally, we have made the large-scale in-domain paired bilingual dialogue dataset publicly available to the research community.