Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
This work provides an incremental improvement for researchers working on cross-domain sentiment analysis.
This paper addresses cross-domain sentiment classification by proposing a contrastive learning framework that aims to induce domain-invariant classifiers. The method achieves new state-of-the-art results on standard benchmarks.
Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal classifiers rather than distribution matching. To this end, we introduce in-domain contrastive learning and entropy minimization. Also, we find through ablation studies that these two techniques behaviour differently in case of large label distribution shift and conclude that the best practice is to choose one of them adaptively according to label distribution shift. The new state-of-the-art results our model achieves on standard benchmarks show the efficacy of the proposed method.