Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation

TL;DR

This paper investigates the effectiveness of existing domain adaptation techniques in unsupervised neural machine translation and proposes modifications to enhance domain-specific UNMT performance.

Contribution

It provides a systematic analysis of domain adaptation scenarios in UNMT and introduces improved methods tailored for domain-specific translation tasks.

Findings

Existing domain adaptation methods can be effective in UNMT.

Modified methods outperform baseline adaptation techniques.

Different domain scenarios require tailored adaptation strategies.

Abstract

Domain adaptation has been well-studied in supervised neural machine translation (SNMT). However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs. Besides the inconsistent domains between training data and test data for SNMT, there sometimes exists an inconsistent domain between two monolingual training data for UNMT. In this work, we empirically show different scenarios for unsupervised neural machine translation. Based on these scenarios, we revisit the effect of the existing domain adaptation methods including batch weighting and fine tuning methods in UNMT. Finally, we propose modified methods to improve the performances of domain-specific UNMT systems.