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

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.

Submitted to EACL 2017 short paper

References in corpus (2)

• Effective Approaches to Attention-based Neural Machine Translation
• Sequence-Level Knowledge Distillation

Cited by in corpus (10)

• A Survey of Domain Adaptation for Neural Machine Translation
• An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
• Neural Machine Translation Training in a Multi-Domain Scenario
• Exploring Benefits of Transfer Learning in Neural Machine Translation
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
• Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation
• Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
• Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation
• Iterative Dual Domain Adaptation for Neural Machine Translation
• SYSTRAN Purely Neural MT Engines for WMT2017