BriefGPT.xyz
Aug, 2019
低资源机器翻译中的语法差异处理
Handling Syntactic Divergence in Low-resource Machine Translation
HTML
PDF
Chunting Zhou, Xuezhe Ma, Junjie Hu, Graham Neubig
TL;DR
本文提出一种简单但有效的方法,即将目标语句重新排序以匹配源语序,并将其作为另外一种训练时的监督信号,从而在模拟低资源日语 - 英语和真实低资源维吾尔 - 英语语种中获得显着改进。
Abstract
Despite impressive empirical successes of
neural machine translation
(NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs.
data augmentation
methods suc
→