Reducing Spurious Correlations for Aspect-Based Sentiment Analysis with Variational Information Bottleneck and Contrastive Learning

by   Mingshan Chang, et al.

Deep learning techniques have dominated the literature on aspect-based sentiment analysis (ABSA), yielding state-of-the-art results. However, these deep models generally suffer from spurious correlation problems between input features and output labels, which creates significant barriers to robustness and generalization capability. 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. To verify the effectiveness of our CVIB method, we conduct extensive experiments on five benchmark ABSA datasets and the experimental results show that our approach achieves better performance than the strong competitors in terms of overall prediction performance, robustness, and generalization.


page 4

page 8


Energy-Based Contrastive Learning of Visual Representations

Contrastive learning is a method of learning visual representations by t...

A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis

Aspect-Based Sentiment Analysis is a fine-grained sentiment analysis tas...

Self-consistent Reasoning For Solving Math Word Problems

Math word problems (MWPs) is a task that automatically derives solution ...

SelfReg: Self-supervised Contrastive Regularization for Domain Generalization

In general, an experimental environment for deep learning assumes that t...

Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure

Generative models have demonstrated impressive results on Aspect-based S...

Masked Reconstruction Contrastive Learning with Information Bottleneck Principle

Contrastive learning (CL) has shown great power in self-supervised learn...

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Aspect-based sentiment analysis (ABSA) aims at automatically inferring t...

Please sign up or login with your details

Forgot password? Click here to reset