# CMV-Fuse: Cross Modal-View Fusion of AMR, Syntax, and Knowledge Representations for Aspect Based Sentiment Analysis

arXiv: https://arxiv.org/abs/2512.06679 · HTML: https://mlsanity.com/paper/2512.06679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 7 Dec 2025.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [Graph Pre-training for AMR Parsing and Generation](https://mlsanity.com/paper/2203.07836/) (2022)
- [Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments](https://mlsanity.com/paper/2106.06002/) (2021)
- [Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2407.10347/) (2024)

## Abstract (arXiv)

Natural language understanding inherently depends on integrating multiple complementary perspectives spanning from surface syntax to deep semantics and world knowledge. However, current Aspect-Based Sentiment Analysis (ABSA) systems typically exploit isolated linguistic views, thereby overlooking the intricate interplay between structural representations that humans naturally leverage. We propose CMV-Fuse, a Cross-Modal View fusion framework that emulates human language processing by systematically combining multiple linguistic perspectives. Our approach systematically orchestrates four linguistic perspectives: Abstract Meaning Representations, constituency parsing, dependency syntax, and semantic attention, enhanced with external knowledge integration. Through hierarchical gated attention fusion across local syntactic, intermediate semantic, and global knowledge levels, CMV-Fuse captures both fine-grained structural patterns and broad contextual understanding. A novel structure aware multi-view contrastive learning mechanism ensures consistency across complementary representations while maintaining computational efficiency. Extensive experiments demonstrate substantial improvements over strong baselines on standard benchmarks, with analysis revealing how each linguistic view contributes to more robust sentiment analysis.