Abstract
Formality is one of the most important linguistic properties to determine the naturalness of translation. Although a target-side context contains formality-related tokens, the sparsity within the context makes it difficult for context-aware neural machine translation (NMT) models to properly discern them. In this paper, we introduce a novel training method to explicitly inform the NMT model by pinpointing key informative tokens using a formality classifier. Given a target context, the formality classifier guides the model to concentrate on the formality-related tokens within the context. Additionally, we modify the standard cross-entropy loss, especially toward the formality-related tokens obtained from the classifier. Experimental results show that our approaches not only improve overall translation quality but also reflect the appropriate formality from the target context.- Anthology ID:
- 2023.findings-emnlp.494
- 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:
- 7384–7392
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.494
- DOI:
- 10.18653/v1/2023.findings-emnlp.494
- Cite (ACL):
- Dohee Kim, Yujin Baek, Soyoung Yang, and Jaegul Choo. 2023. Towards Formality-Aware Neural Machine Translation by Leveraging Context Information. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7384–7392, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Towards Formality-Aware Neural Machine Translation by Leveraging Context Information (Kim et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.494.pdf