Abstract
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.- Anthology ID:
- 2023.findings-emnlp.333
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5000–5010
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.333
- DOI:
- 10.18653/v1/2023.findings-emnlp.333
- Cite (ACL):
- Ke Wang, Jun Xie, Yuqi Zhang, and Yu Zhao. 2023. Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5000–5010, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting (Wang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-emnlp.333.pdf