论文标题
与内域对比度学习的跨域情感分类
Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
论文作者
论文摘要
对比学习（CL）已成功地成为一种强大的表示学习方法。在本文中，我们为跨域情感分类提出了一个对比度学习框架。我们的目标是诱导域不变的最佳分类器，而不是分布匹配。为此，我们引入了内域对比度学习和熵最小化。另外，我们通过消融研究发现，这两种技术行为在较大的标签分布转移的情况下有所不同，并得出结论，最好的做法是根据标签分布变化来适应其中一种。我们的模型在标准基准上实现的新最先进的结果显示了该方法的功效。
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.
