Domain specialization: a post-training domain adaptation for Neural Machine Translation

TL;DR

This paper introduces a novel domain specialization method for Neural Machine Translation that enhances adaptation speed and accuracy, particularly useful in post-editing workflows, by focusing on targeted domain-specific tuning.

Contribution

The paper proposes the concept of domain specialization as a new approach to post-training domain adaptation in NMT, demonstrating its potential benefits.

Findings

Faster learning speed in domain adaptation

Improved adaptation accuracy in NMT

Effective for human post-editing workflows

Abstract

Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neural Machine Translation (NMT), we introduce a new notion of domain adaptation that we call "specialization" and which is showing promising results both in the learning speed and in adaptation accuracy. In this paper, we propose to explore this approach under several perspectives.