Paper ID | HLT-8.1 | ||
Paper Title | MODELING HOMOPHONE NOISE FOR ROBUST NEURAL MACHINE TRANSLATION | ||
Authors | Wenjie Qin, Soochow University, China; Xiang Li, Yuhui Sun, Xiaomi AI Lab, China; Deyi Xiong, Tianjin University, China; Jianwei Cui, Bin Wang, Xiaomi AI Lab, China | ||
Session | HLT-8: Speech Translation 2: Aspects | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 14:00 - 14:45 | ||
Presentation Time: | Wednesday, 09 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Human Language Technology: [HLT-MTSW] Machine Translation for Spoken and Written Language | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In this paper, we propose a robust neural machine translation (NMT) framework to deal with homophone errors. The framework consists of a homophone noise detector and a syllable-aware NMT model. 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 the proposed method not only significantly outperforms baselines on noisy test sets with homophone noise, but also achieves substantial improvements over them on clean texts. |