Pin Ni

University College London

Papers

1

Total Citations

53

H-Index

1

About

Pin Ni is a leading researcher at the intersection of natural language processing, knowledge graphs, and healthcare AI. His most impactful work centers on developing intelligent systems that bridge human language and structured data, exemplified by his highly cited 2022 paper on a "Knowledge Graph and Deep Learning-based Text-to-GraphQL Model for Intelligent Medical Consultation Chatbot" (53 citations). In this work, Ni pioneered the Text-to-GQL (Text2GQL) task, a novel semantic parsing approach that converts patient questions into Graph Query Language queries, enabling direct, efficient communication between users and graph databases. This contribution addresses a critical bottleneck in medical chatbots: translating complex, natural language queries into precise database operations without human intervention. By integrating deep learning with knowledge graph reasoning, Ni’s model significantly enhances the accuracy and usability of AI-driven consultation systems. His research demonstrates how combining structured knowledge with advanced neural architectures can transform healthcare interactions, making expert information more accessible. With growing recognition for his innovative approach to semantic parsing and graph-based AI, Pin Ni continues to push boundaries in applied natural language understanding, particularly in high-stakes medical domains where precision and reliability are paramount.

Research Focus

Key Achievements

1
H-Index
1
Papers
53
Total Citations
53
Avg Citations/Paper
🏆 Most Cited Paper
Knowledge Graph and Deep Learning-based Text-to-GraphQL Model for Intelligent Medical Consultation Chatbot
53 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: University College London

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago