超越余弦相似度:面向方面的情感分析中的零初始化残差复数投影
Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis
AI总结:
本文提出零初始化残差复数投影与反碰撞掩码角度损失,通过复数空间分离情感极性并增强类别结构一致性,实验表明在ASAP数据集上达到89.23%的Macro-F1分数。
摘要:
面向方面的情感分析(ABSA)面临实值嵌入空间中表示纠缠和假负碰撞的严峻挑战。本文提出一种新颖的框架,包含零初始化残差复数投影(ZRCP)和反碰撞掩码角度损失。我们的方法将文本特征投影到复数语义空间,利用相位分离情感极性,同时通过正则化振幅确保方面类别内的结构一致性。为缓解此问题,我们引入反碰撞掩码,保留同极性方面的一致性,同时显著扩大对立极性间的判别边缘。在ASAP数据集上的实验结果表明,我们的框架实现了89.23%的Macro-F1分数,优于稳健的基线方法。
英文摘要:
Aspect-Based Sentiment Analysis (ABSA) faces critical challenges due to representation entanglement and false-negative collisions in real-valued embedding spaces. In this paper, we propose a novel framework featuring a Zero-Initialized Residual Complex Projection (ZRCP) and an Anti-collision Masked Angle Loss. Our approach projects textual features into a complex semantic space, utilizing the phase to isolate sentiment polarities while regularizing the amplitude to ensure structural consistency within aspect categories. To mitigate this, we introduce an anti-collision mask that preserves intra-polarity aspect cohesion while significantly expanding the discriminative margin between opposing polarities. Experimental results on the ASAP dataset demonstrate that our framework achieves a state-of-the-art Macro-F1 score of 0.8923, outperforming robust baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。