Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis

TL;DR

This paper introduces DCRAN, a deep learning model that enhances aspect-based sentiment analysis by incorporating deep contextual and relation-aware information, significantly improving performance on benchmark datasets.

Contribution

The paper proposes a novel Deep Contextualized Relation-Aware Network with self-supervised strategies for better handling multiple aspects in ABSA.

Findings

DCRAN outperforms previous state-of-the-art methods on benchmarks.

The model effectively captures deep contextual relations among aspects and opinions.

Self-supervised strategies improve multi-aspect detection accuracy.

Abstract

Existing works for aspect-based sentiment analysis (ABSA) have adopted a unified approach, which allows the interactive relations among subtasks. However, we observe that these methods tend to predict polarities based on the literal meaning of aspect and opinion terms and mainly consider relations implicitly among subtasks at the word level. In addition, identifying multiple aspect-opinion pairs with their polarities is much more challenging. Therefore, a comprehensive understanding of contextual information w.r.t. the aspect and opinion are further required in ABSA. In this paper, we propose Deep Contextualized Relation-Aware Network (DCRAN), which allows interactive relations among subtasks with deep contextual information based on two modules (i.e., Aspect and Opinion Propagation and Explicit Self-Supervised Strategies). Especially, we design novel self-supervised strategies for ABSA, which have strengths in dealing with multiple aspects. Experimental results show that DCRAN significantly outperforms previous state-of-the-art methods by large margins on three widely used benchmarks.