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

2025-12-07

AI Summary

Existing Aspect-Based Sentiment Analysis (ABSA) methods typically employ isolated linguistic perspectives, neglecting synergistic modeling among abstract semantics, syntactic structures, and external knowledge. Method: This paper proposes CMV-Fuse, the first framework to jointly model multi-perspective representations—Abstract Meaning Representation (AMR), constituency/dependency syntax, and external knowledge—via cross-modal fusion. It introduces a hierarchical gated attention mechanism to coordinate local syntactic, intermediate semantic, and global knowledge representations, and incorporates structure-aware multi-view contrastive learning to enhance representational robustness and consistency. Contribution/Results: CMV-Fuse achieves significant improvements over strong baselines across multiple standard ABSA benchmarks. Ablation studies confirm the complementary roles of each linguistic perspective and validate the framework’s effectiveness.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

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.

Problem

• Fuses multiple linguistic views for aspect-based sentiment analysis.
• Integrates AMR, syntax, and knowledge representations systematically.
• Enhances structural and contextual understanding in sentiment analysis.

Innovation

• Fuses AMR, constituency, dependency, and semantic attention
• Hierarchical gated attention across syntactic, semantic, knowledge levels
• Structure-aware multi-view contrastive learning for representation consistency