Unsupervised Domain Adaptation with Feature Embeddings

Code

• github.com/yiyang-gt/feat2vec
  none★ 33

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 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.

Tasks

Reproductions