一种基于CLCA-CGCN的行为极性分类方法
The CLCA-CGCN model, which integrates contextual attention and contrastive learning, solves the challenge of classifying behavioral polarity in complex legal texts, improving classification accuracy and efficiency, and is applicable to behavioral polarity analysis of legal texts.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF ELECTRONICS SCI & TECH OF CHINA
- Filing Date
- 2024-07-08
- Publication Date
- 2026-07-17
AI Technical Summary
Existing behavioral polarity classification methods face challenges when dealing with complex legal texts, including complex terminology, complex contextual dependencies, ambiguity and abstraction, difficulty in processing long texts, and data scarcity and imbalance, resulting in low classification accuracy and efficiency.
We employ a behavior polarity classification model that combines contextual attention-based contrastive learning (CLCA) and CGCN. By designing a special attention mechanism, an improved contextual attention module, a CGCN network, and a contrastive learning strategy, we enhance the model's accuracy and efficiency in classifying complex legal texts.
It effectively handles contextual dependencies in legal texts, enhances word embedding representations, alleviates information compression problems, and improves the accuracy and stability of the model in classifying behavioral polarity in complex legal texts.
Smart Images
Figure CN118916737B_ABST