Unsupervised Domain Adaptation with Feature Embeddings

2014/12/14 by Yi Yang, Jacob Eisenstein, Yang, Yi +1
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1412.4385

openalex publication_date 2014/12/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Representation Learning: A Review and New Perspectives

Related

• Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
• Domain Adaptation via Prompt Learning
• Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
• UDApter -- Efficient Domain Adaptation Using Adapters
• Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation