Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation

WMT, 2018.

被引用19|引用|浏览37|来源
EI

摘要

To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each componentu0027s contribution to, and capacity for, domain adaptation. We find that freezing any single component during continued training h...更多

代码

数据

您的评分 :
0

 

标签
评论