BriefGPT.xyz
Sep, 2018
神经机器翻译中冻结子网络以分析领域自适应
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
HTML
PDF
Brian Thompson, Huda Khayrallah, Antonios Anastasopoulos, Arya McCarthy, Kevin Duh...
TL;DR
分析神经机器翻译系统的主要组件及其对领域适应性的贡献和容量，发现继续训练对性能的影响不大，并且当单个组件适应时性能惊人的好。发现继续训练不会将模型移动得非常远离域外模型，这表明域外模型可以为新域提供良好的通用初始化。
Abstract
To better understand the effectiveness of
continued training
, we analyze the major components of a
neural machine translation
system (the
encoder
→