Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts
This addresses the high cost of fine-tuning for domain adaptation in machine translation, offering a zero-shot solution that is incremental in its approach.
The paper tackles domain adaptation in neural machine translation by proposing a non-tuning paradigm using retrieved phrase-level prompts, which improves domain-specific translation by 6.2 BLEU scores and translation constraint accuracy by 11.5% without extra training.
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.