Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts

TL;DR

This paper introduces a prompt-based domain adaptation method for neural machine translation that improves translation quality and constraints without additional training by retrieving relevant phrase-level prompts.

Contribution

It proposes a non-tuning, prompt-based approach using retrieved phrase-level prompts for effective domain adaptation in neural machine translation.

Findings

Improves domain-specific BLEU scores by 6.2 points

Enhances translation constraint accuracy by 11.5%

Eliminates need for additional training during adaptation

Abstract

Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. In this paper, we propose a non-tuning paradigm, resolving domain adaptation with a prompt-based method. Specifically, we construct a bilingual phrase-level database and retrieve relevant pairs from it as a prompt for the input sentences. By utilizing Retrieved Phrase-level Prompts (RePP), we effectively boost the translation quality. Experiments show that our method improves domain-specific machine translation for 6.2 BLEU scores and improves translation constraints for 11.5% accuracy without additional training.