Let's Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models
This work addresses a specific bottleneck in ABSA for natural language processing applications, offering an incremental improvement with a novel method.
The paper tackles the challenge of precisely determining aspect boundaries in Aspect-Based Sentiment Analysis (ABSA), especially for long aspects in colloquial text, by proposing DiffusionABSA, a diffusion model that extracts aspects step by step, achieving compelling advantages over baselines on eight benchmark datasets.
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.