Let's Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models

TL;DR

This paper introduces DiffusionABSA, a diffusion model that progressively extracts aspect terms and their boundaries in aspect-based sentiment analysis, improving accuracy especially for long and colloquial expressions.

Contribution

The paper presents a novel diffusion-based approach for ABSA that incrementally restores aspect terms and accurately estimates boundaries using a syntax-aware neural network.

Findings

Outperforms baseline models on eight benchmark datasets.

Effectively handles long and colloquial aspect expressions.

Demonstrates the benefits of diffusion models in ABSA tasks.

Abstract

Aspect-Based Sentiment Analysis (ABSA) stands as a crucial task in predicting the sentiment polarity associated with identified aspects within text. However, a notable challenge in ABSA lies in precisely determining the aspects' boundaries (start and end indices), especially for long ones, due to users' colloquial expressions. We propose DiffusionABSA, a novel diffusion model tailored for ABSA, which extracts the aspects progressively step by step. Particularly, DiffusionABSA gradually adds noise to the aspect terms in the training process, subsequently learning a denoising process that progressively restores these terms in a reverse manner. To estimate the boundaries, we design a denoising neural network enhanced by a syntax-aware temporal attention mechanism to chronologically capture the interplay between aspects and surrounding text. Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models. Our code is publicly available at https://github.com/Qlb6x/DiffusionABSA.