用复数空间分离情感极性，解决文本嵌入混淆问题。
Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis
- 将文本特征投影到复数空间，用相位分离情感极性。
- 在ASAP数据集上达到0.8923的宏F1分数，超越现有方法。
- 适合需要精准情感分类的场景，如产品评论分析。
基于方面的情感分析（ABSA）因实值嵌入空间中的表示纠缠和假负例碰撞面临严峻挑战。本文提出一种新框架，包含零初始化残差复数投影（ZRCP）和抗碰撞掩码角度损失。该方法将文本特征映射至复数语义空间，利用相位分离情感极性，同时通过幅度正则化确保方面类别内的结构一致性。为缓解此问题，引入抗碰撞掩码，保持同极性方面内聚性，显著扩大对立极性间的判别间隔。在ASAP数据集上的实验结果表明，该框架实现0.8923的最优宏观F1分数，优于多个稳健基线模型。
原文摘要 · Abstract (English)
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.
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。