Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis
This work addresses a domain-specific problem in natural language processing for sentiment analysis, offering a novel method to improve performance on high-frequency aspects.
The paper tackled representation entanglement and false-negative collisions in Aspect-Based Sentiment Analysis by proposing a framework with Zero-Initialized Residual Complex Projection and Anti-collision Masked Angle Loss, achieving a state-of-the-art Macro-F1 score of 0.8851.
Aspect-Based Sentiment Analysis (ABSA) is fundamentally challenged by representation entanglement, where aspect semantics and sentiment polarities are often conflated in real-valued embedding spaces. Furthermore, standard contrastive learning suffers from false-negative collisions, severely degrading performance on high-frequency aspects. In this paper, we propose a novel framework featuring a Zero-Initialized Residual Complex Projection (ZRCP) and an Anti-collision Masked Angle Loss,inspired by quantum projection and entanglement ideas. Our approach projects textual features into a complex semantic space, systematically utilizing the phase to disentangle sentiment polarities while allowing the amplitude to encode the semantic intensity and lexical richness of subjective descriptions. To tackle the collision bottleneck, we introduce an anti-collision mask that elegantly preserves intra-polarity aspect cohesion while expanding the inter-polarity discriminative margin by over 50%. Experimental results demonstrate that our framework achieves a state-of-the-art Macro-F1 score of 0.8851. Deep geometric analyses further reveal that explicitly penalizing the complex amplitude catastrophically over-regularizes subjective representations, proving that our unconstrained-amplitude and phase-driven objective is crucial for robust, fine-grained sentiment disentanglement.