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

arXiv: https://arxiv.org/abs/2603.28205 · HTML: https://mlsanity.com/paper/2603.28205/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [Encoding word order in complex embeddings](https://mlsanity.com/paper/1912.12333/) (2019)
- [Exploiting Adaptive Contextual Masking for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2402.13722/) (2024)

## Abstract (arXiv)

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.