Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
This addresses a specific limitation in cross-domain sentiment analysis for NLP researchers, though it appears incremental as a modification to existing DIRL methods.
The authors tackled the problem where domain-invariant representation learning (DIRL) can harm cross-domain sentiment analysis when label distributions change across domains, and proposed a weighted DIRL (WDIRL) framework that improved performance on extensive tasks.
Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may harm domain adaptation when the label distribution $\rm{P}(\rm{Y})$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing SOTA DIRL models to WDIRL. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.