In this paper, we propose a robust neural machine translation (NMT) framework. The framework consists of a homophone noise detector and a syllable-aware NMT model to homophone errors. The detector identifies potential homophone errors in a textual sentence and converts them into syllables to form a mixed sequence that is then fed into the syllable-aware NMT. Extensive experiments on Chinese->English translation demonstrate that our proposed method not only significantly outperforms baselines on noisy test sets with homophone noise, but also achieves a substantial improvement on clean text.
@article{arxiv.2012.08396,
title = {Modeling Homophone Noise for Robust Neural Machine Translation},
author = {Wenjie Qin and Xiang Li and Yuhui Sun and Deyi Xiong and Jianwei Cui and Bin Wang},
journal= {arXiv preprint arXiv:2012.08396},
year = {2020}
}