Unified Model Learning for Various Neural Machine Translation

TL;DR

This paper introduces UMLNMT, a unified neural machine translation model capable of handling multiple translation tasks simultaneously, reducing deployment costs and outperforming dataset-specific models on various benchmarks.

Contribution

The paper proposes a versatile, unified NMT model that jointly trains across diverse tasks, enabling on-demand translation and achieving superior performance with fewer models.

Findings

UMLNMT outperforms dataset-specific models on seven translation tasks.

It reduces model deployment costs significantly.

Achieves competitive or better results than state-of-the-art methods.

Abstract

Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat translation). Although the dataset-specific models have achieved impressive performance, it is cumbersome as each dataset demands a model to be designed, trained, and stored. In this work, we aim to unify these translation tasks into a more general setting. Specifically, we propose a ``versatile'' model, i.e., the Unified Model Learning for NMT (UMLNMT) that works with data from different tasks, and can translate well in multiple settings simultaneously, and theoretically it can be as many as possible. Through unified learning, UMLNMT is able to jointly train across multiple tasks, implementing intelligent on-demand translation. On seven widely-used translation tasks, including sentence translation, document translation, and chat translation, our UMLNMT results in substantial improvements over dataset-specific models with significantly reduced model deployment costs. Furthermore, UMLNMT can achieve competitive or better performance than state-of-the-art dataset-specific methods. Human evaluation and in-depth analysis also demonstrate the superiority of our approach on generating diverse and high-quality translations. Additionally, we provide a new genre translation dataset about famous aphorisms with 186k Chinese->English sentence pairs.