DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis
This work addresses boundary insensitivity in multi-word aspect/opinion terms for ABSA, a known bottleneck in unified sentiment analysis.
DiffuSent proposes a non-auto-regressive diffusion framework for Aspect-Based Sentiment Analysis that formulates all subtasks as boundary denoising processes, achieving consistent improvements over generative and span-based systems with up to 181x faster inference and +2.48 F1 gain on multi-word triplets.
Aspect-Based Sentiment Analysis (ABSA) encompasses seven distinct subtasks, each focusing on different extracted elements. Despite the proven success of generative models in unified aspect sentiment analysis, existing approaches often rely on auto-regressive token-by-token generation without grasping the whole information of the aspect and opinion terms, resulting in boundary insensitivity, particularly in context of multi-word aspect and opinion terms. To address these issues, we present DiffuSent, a non-auto-regressive diffusion framework that systematically formulates all ABSA subtasks as boundary denoising diffusion processes, progressively refining boundaries over noisy states. Furthermore, we introduce a contrastive denoising training strategy which effectively address duplicate predictions with subtle variations introduced by diffusion process. Extensive experiments across 28 settings (7 subtasks x 4 datasets) demonstrate that DiffuSent achieves delivers consistent improvements over the strongest generative and span-based systems. DiffuSent exhibits notable gains on multi-word triplets, achieving an average improvement of +2.48 F1, and maintains robust extraction accuracy in sentences containing multiple sentiment triplets. Moreover, the non-auto-regressive decoding enables substantial efficiency benefits, reaching up to 181 times faster inference than auto-regressive generative baselines