%0 Journal Article
%T Unsupervised Domain Adaptation with Feature Embeddings
%A Yi Yang
%A Jacob Eisenstein
%J Computer Science
%D 2014
%I arXiv
%X 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 by task-specific heuristics. We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP problems.
%U http://arxiv.org/abs/1412.4385v3