发表机构
Northeastern University, China（东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于Jev冻结模型的类型化决策方法，无需文本生成即可在维度ABSA任务上取得领先性能，通过系数校准实现低误差与高F1分数。
AI 中文摘要
基于方面的情感分析（ABSA）在很大程度上已转向文本生成。我们证明，竞争性的维度ABSA并不需要文本生成。使用Jev，一个冻结的模型，它通过评分标准分数、标签概率和是/否判断来回答类型化问题，我们将SemEval-2026任务III轨道A的所有三个子任务分解为这样的决策，并通过在CPU上拟合的488个系数将其与标注方案对齐，无需文本生成和骨干网络微调。在涵盖六种语言的十个语料库上的效价-唤醒回归中，该系统达到1.0645的均方根误差（RMSE），是所有参赛系统中最低的聚合误差。在三元组和四元组提取中，它分别达到52.09和44.06的连续F1分数，超过了微调的Llama-3.3-70B和GPT-OSS-120B基线。分析和消融实验显示了准确性的来源：监督校准大致将原始回归误差减半，精确的效价-唤醒只会给提取增加4.5的F1分数，而跨度边界证据的学习组合（而非任何单一信号）支撑了提取系统。
英文摘要
Aspect-based sentiment analysis (ABSA) has largely turned to text generation. We show that competitive dimensional ABSA does not need it. Using Jev, a frozen model that answers typed questions with rubric scores, label probabilities, and yes/no judgments, we decompose all three tasks of SemEval-2026 Task III Track A into such decisions and align them with the annotation scheme through 488 coefficients fitted on CPU, with no text generation and no backbone tuning. On valence-arousal regression over ten corpora in six languages, the system reaches 1.0645 RMSE, the lowest aggregate error of any participating system. On triplet and quadruplet extraction, it reaches 52.09 and 44.06 continuous F1, above fine-tuned Llama-3.3-70B and GPT-OSS-120B baselines. Analyses and ablations show where the accuracy comes from: supervised calibration roughly halves the raw regression error, exact valence-arousal would add only 4.5 F1 to extraction, and the learned combination of span-boundary evidence, not any single signal, carries the extraction systems.
Comments14 pages, 2 figures, 9 tables. Code: https://github.com/ZhangYiqun018/jev-dimabsa
