BriefGPT.xyz
Dec, 2014
基于特征嵌入的无监督域适应
Unsupervised Domain Adaptation with Feature Embeddings
HTML
PDF
Yi Yang, Jacob Eisenstein
TL;DR
本研究提出一种基于特征嵌入、利用NLP问题中常见的特征模板结构的新颖但简单的特征学习方法来提高无监督领域自适应的性能。
Abstract
representation learning
is the dominant technique for
unsupervised domain adaptation
, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected
→