Unsupervised Domain Adaptation with Feature Embeddings
This work addresses domain adaptation in NLP, offering a more effective solution for scenarios where labeled data is scarce across domains, though it appears incremental as it builds on representation learning techniques.
The paper tackled the problem of unsupervised domain adaptation by proposing a novel feature embedding approach that exploits NLP feature template structures, achieving better performance than existing methods that rely on task-specific heuristics for pivot feature selection.
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.