DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis

[2606.01323] DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2606.01323 (cs) [Submitted on 31 May 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis Authors: Shu Long , Yanglei Gan , Xuchuan Zhou View PDF HTML (experimental) Abstract: 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 Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2606.01323 [cs.CL] (or arXiv:2606.01323v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.01323 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yanglei Gan [ view email ] [v1] Sun, 31 May 2026 16:15:03 UTC (3,738 KB) [v2] Fri, 28 Aug 2026 09:54:04 UTC (3,746 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis#682704
• Semantic Variational Bayes Based on Semantic Information G Theory for Solving Latent Variables#183160
• Issue-Specific Polarization and Cohesion in a Multi-Party Legislature: Integrating the Latent Space Item Response Model with Topic-Based Regression#1048317
• Overseas reception of English translations of Journey to the West: Temporal dynamics, cross-platform sentiment patterns, and topic modeling.#122723
• Corpus-Based Studies on Language Varieties#341545