BriefGPT.xyz
Apr, 2019
利用领域不变和特定信息提升领域自适应翻译
Improving Domain Adaptation Translation with Domain Invariant and Specific Information
HTML
PDF
Shuhao Gu, Yang Feng, Qun Liu
TL;DR
本文提出了一种基于编码器-解码器框架的方法,以明确建模领域特定特征和常用特征的信息分离,通过敌对训练强化信息分离和机器翻译的表现,并在多个数据集上表现出优越的性能。
Abstract
In
domain adaptation
for
neural machine translation
, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitl
→