Abstract
The literature on aspect-based sentiment analysis (ABSA) has been overwhelmed by deep neural networks, yielding state-of-the-art results for ABSA. However, these deep models are susceptible to learning spurious correlations between input features and output labels, which in general suffer from poor robustness and generalization. In this paper, we propose a novel Contrastive Variational Information Bottleneck framework (called CVIB) to reduce spurious correlations for ABSA. The proposed CVIB framework is composed of an original network and a self-pruned network, and these two networks are optimized simultaneously via contrastive learning. Concretely, we employ the Variational Information Bottleneck (VIB) principle to learn an informative and compressed network (self-pruned network) from the original network, which discards the superfluous patterns or spurious correlations between input features and prediction labels. Then, self-pruning contrastive learning is devised to pull together semantically similar positive pairs and push away dissimilar pairs, where the representations of the anchor learned by the original and self-pruned networks respectively are regarded as a positive pair while the representations of two different sentences within a mini-batch are treated as a negative pair. Extensive experiments on five benchmark ABSA datasets demonstrate that our CVIB method achieves better performance than the strong competitors in terms of overall prediction performance, robustness, and generalization.
Abstract (translated)
面向属性的情感分析文献已经受到深度神经网络的淹没,取得了ABSA领域最先进的结果。然而,这些深度模型容易学习输入特征和输出标签之间的伪相关,这通常会导致 poor 的鲁棒性和泛化能力。在本文中,我们提出了一种全新的对比变异信息瓶颈框架(称为CVIB),以减少ABSA中的伪相关。 proposed CVIB框架由原始网络和自我修剪网络组成,这两个网络同时通过对比学习优化。具体来说,我们采用了Variational Information Bottleneck (VIB)原则从原始网络中学习一个 informative 且压缩的网络(自我修剪网络),该网络抛弃了输入特征和预测标签之间的多余的模式或伪相关。然后,自我修剪对比学习旨在将语义上相似的正对和排斥不相似的负对结合起来,其中原始和自我修剪网络分别学习的锚的表示被视为正对,而在一个迷你批量中两个不同句子的表示被视为负对。对五个基准ABSA数据集的广泛实验表明,我们的CVIB方法在整体预测性能、鲁棒性和泛化能力方面比强大的竞争对手表现更好。
URL
https://arxiv.org/abs/2303.02846
