用扩散模型统一处理情感分析，提升多词边界识别与效率
DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis
- 将所有情感分析任务建模为边界去噪过程，非自回归生成
- 多词情感三元组平均提升2.48 F1，复杂句中提取更稳定
- 推理速度比自回归模型快181倍，适合实时应用
方面情感分析（ABSA）包含七个不同子任务，各自关注不同抽取元素。尽管生成模型在统一方面情感分析中表现优异，但现有方法多依赖自回归逐标记生成，难以把握方面和观点项的完整信息，导致边界不敏感，尤其在多词方面和观点项情境下。为此，我们提出DiffuSent，一种非自回归扩散框架，将所有ABSA子任务系统地建模为边界去噪扩散过程，通过逐步修正噪声状态来精炼边界。此外，引入对比去噪训练策略，有效缓解扩散过程带来的细微差异导致的重复预测问题。在28个设置（7个子任务×4个数据集）上的大量实验表明，DiffuSent在强生成与跨度基模型上均实现一致提升。在多词三元组上平均提升2.48 F1，且在含多个情感三元组的句子中保持稳健提取精度。同时，非自回归解码带来显著效率优势，推理速度最高达自回归基线的181倍。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。