Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model

TL;DR

This paper introduces a joint aspect-based sentiment analysis model that leverages dual encoders to focus on both shared features and differences, significantly improving performance on benchmark datasets.

Contribution

The novel dual-encoder architecture explicitly models the difference between subtasks, enhancing joint ABSA performance beyond existing encoder-sharing methods.

Findings

Outperforms previous state-of-the-art on four datasets

Demonstrates robustness across different datasets

Effectively models subtask differences for improved accuracy

Abstract

Aspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources and reduce the error propagation in the pipeline. However, most of the existing joint models only focus on the benefits of encoder sharing between subtasks but ignore the difference. Therefore, we propose a joint ABSA model, which not only enjoys the benefits of encoder sharing but also focuses on the difference to improve the effectiveness of the model. In detail, we introduce a dual-encoder design, in which a pair encoder especially focuses on candidate aspect-opinion pair classification, and the original encoder keeps attention on sequence labeling. Empirical results show that our proposed model shows robustness and significantly outperforms the previous state-of-the-art on four benchmark datasets.