Runzhu Wang
Papers
1
Total Citations
5
H-Index
1
About
Runzhu Wang’s research lies at the intersection of natural language processing and knowledge-enhanced representation learning, with a particular focus on improving how machines understand and compare long-form text. In her most cited work, “Learning Long-text Semantic Similarity with Multi-Granularity Semantic Embedding Based on Knowledge Enhancement” (2020), Wang introduced a novel framework that integrates external knowledge into multi-granularity embeddings, enabling more accurate semantic similarity assessments for lengthy documents. This contribution addresses a critical bottleneck in NLP—the difficulty of capturing nuanced meaning across extended passages—and has garnered 5 citations, establishing a foundation for subsequent work in knowledge-aware text analysis. Wang’s approach stands out for its ability to bridge granular linguistic features with high-level conceptual understanding, a technique that holds promise for applications in information retrieval, document summarization, and question answering. Her collaboration with researchers from Chongqing University and Chongqing Megalight Technology reflects a commitment to bridging academic innovation with practical, industry-driven solutions. As a rising voice in semantic representation, Wang’s work continues to inspire new directions in long-text understanding and knowledge-enhanced learning.
Research Focus
Key Achievements
Top Papers
- 1