Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis

TL;DR

This paper introduces a novel complex projection framework with anti-collision mechanisms for Aspect-Based Sentiment Analysis, achieving state-of-the-art results by better disentangling sentiment representations.

Contribution

The proposed Zero-Initialized Residual Complex Projection and Anti-collision Mask effectively address entanglement and false negatives in ABSA, advancing the field.

Findings

Achieves a Macro-F1 score of 0.8923 on the ASAP dataset.

Outperforms existing baselines in sentiment classification.

Effectively disentangles sentiment polarities in complex semantic space.

Abstract

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.