A Survey of Domain Adaptation for Neural Machine Translation

TL;DR

This paper surveys various domain adaptation techniques for neural machine translation, addressing the challenge of improving translation quality in domain-specific scenarios with limited in-domain data.

Contribution

It provides a comprehensive overview of current domain adaptation methods for NMT, highlighting recent advances and research directions.

Findings

Summarizes key domain adaptation techniques for NMT.

Identifies challenges and future research directions.

Highlights effectiveness of adaptation methods in specific domains.

Abstract

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.