Modeling Homophone Noise for Robust Neural Machine Translation

TL;DR

This paper introduces a novel homophone noise detection and syllable-aware neural machine translation framework that enhances translation robustness against homophone errors in Chinese-English translation tasks.

Contribution

It presents a combined homophone noise detector and syllable-aware NMT model, improving translation accuracy on noisy and clean texts.

Findings

Significant performance gains on noisy test sets.

Improved translation quality on clean text.

Effective detection and correction of homophone errors.

Abstract

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.