BriefGPT.xyz
Oct, 2019
通过数据增强提高神经机器翻译的鲁棒性：超越回译
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation
HTML
PDF
Zhenhao Li, Lucia Specia
TL;DR
本文探讨了神经机器翻译以及如何提高其对于噪声输入的鲁棒性，提出了新的数据扩充方法以及通过利用外部数据中的噪声来加强模型鲁棒性。
Abstract
neural machine translation
(NMT) models have been proved strong when translating clean texts, but they are very sensitive to
noise
in the input. Improving NMT models
→