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

TL;DR

This paper introduces a novel contrastive cross-channel data augmentation framework for aspect-based sentiment analysis, improving model robustness and accuracy by generating synthetic multi-aspect sentences and filtering low-quality samples.

Contribution

The proposed C3 DA framework leverages in-domain generative models and cross-channel sentence generation to enhance ABSA performance, addressing multi-aspect challenges with contrastive learning.

Findings

Outperforms baselines by about 1% in accuracy and Macro-F1

Effective in generating high-quality synthetic data for ABSA

Enhances model robustness against multi-aspect interference

Abstract

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other. To mitigate this issue, we design a novel training framework, called Contrastive Cross-Channel Data Augmentation (C3 DA), which leverages an in-domain generator to construct more multi-aspect samples and then boosts the robustness of ABSA models via contrastive learning on these generated data. In practice, given a generative pretrained language model and some limited ABSA labeled data, we first employ some parameter-efficient approaches to perform the in-domain fine-tuning. Then, the obtained in-domain generator is used to generate the synthetic sentences from two channels, i.e., Aspect Augmentation Channel and Polarity Augmentation Channel, which generate the sentence condition on a given aspect and polarity respectively. Specifically, our C3 DA performs the sentence generation in a cross-channel manner to obtain more sentences, and proposes an Entropy-Minimization Filter to filter low-quality generated samples. Extensive experiments show that our C3 DA can outperform those baselines without any augmentations by about 1% on accuracy and Macro- F1. Code and data are released in https://github.com/wangbing1416/C3DA.