Mere Contrastive Learning for Cross-Domain Sentiment Analysis
This addresses the problem of labeled data scarcity in sentiment analysis across domains, though it appears incremental as it adapts contrastive learning to an existing task.
The paper tackles cross-domain sentiment analysis by proposing a modified contrastive learning objective that pushes same-class sentence representations closer and different-class ones apart, achieving state-of-the-art performance on two datasets.
Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for the task, which suffer from instability and poor generalization. In this paper, we explore contrastive learning on the cross-domain sentiment analysis task. We propose a modified contrastive objective with in-batch negative samples so that the sentence representations from the same class will be pushed close while those from the different classes become further apart in the latent space. Experiments on two widely used datasets show that our model can achieve state-of-the-art performance in both cross-domain and multi-domain sentiment analysis tasks. Meanwhile, visualizations demonstrate the effectiveness of transferring knowledge learned in the source domain to the target domain and the adversarial test verifies the robustness of our model.