Towards Formality-Aware Neural Machine Translation by Leveraging Context Information
Dohee Kim, Yujin Baek, Soyoung Yang, Jaegul Choo
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.
BibTeX
@inproceedings{
kim2023towards,
title={Towards Formality-Aware Neural Machine Translation by Leveraging Context Information},
author={Dohee Kim and Yujin Baek and Soyoung Yang and Jaegul Choo},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=XmS9J3Lvip}
}