Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

Abstract

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment classification. To the best of our knowledge, CLIM is the first to adopt contrastive learning for natural language processing (NLP) tasks across domains. Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction. Furthermore, MIM is able to maintain a relatively balanced distribution of the model's prediction, and enlarges the margin between classes on the target domain. The larger margin increases our model's robustness and enables the same classifier to be optimal across domains. Consequently, we achieve new state-of-the-art results on the Amazon-review dataset as well as the airlines dataset, showing the efficacy of our proposed method CLIM.

arXiv comment5 pages, 1 figure

References in corpus (9)

• A Simple Framework for Contrastive Learning of Visual Representations
• Momentum Contrast for Unsupervised Visual Representation Learning
• Return of Frustratingly Easy Domain Adaptation
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Rethinking Distributional Matching Based Domain Adaptation
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
• Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification