Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting
This work addresses domain-specific translation challenges for users of neural machine translation systems, though it is incremental in nature.
The authors tackled the problem of enhancing neural machine translation by integrating multiple types of knowledge using prompting, resulting in significant improvements in translation quality and terminology match accuracy over strong baselines on English-Chinese and English-German tasks.
Improving neural machine translation (NMT) systems with prompting has achieved significant progress in recent years. In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the performance with prompting. We propose a unified framework, which can integrate effectively multiple types of knowledge including sentences, terminologies/phrases and translation templates into NMT models. We utilize multiple types of knowledge as prefix-prompts of input for the encoder and decoder of NMT models to guide the translation process. The approach requires no changes to the model architecture and effectively adapts to domain-specific translation without retraining. The experiments on English-Chinese and English-German translation demonstrate that our approach significantly outperform strong baselines, achieving high translation quality and terminology match accuracy.