Borui Zhang: Home

Self-intro:

I’m the Natural Language Processing (NLP) Specialist at George A. Smathers Libraries, University of Florida. I specialize in NLP with a focus on named entity recognition (NER), LLM fine-tuning, information retrieval, data structuring, and feature engineering. My work applies AI to improve research workflows, digital collections, and interdisciplinary scholarship. I’ve collaborated on projects in medicine, agriculture, biology, and the humanities, and I’m also engaged in research on low-resource languages such as Nepal Bhasa and Cantonese. My goal is to build adaptable NLP systems that enhance research productivity, support data-driven decision-making, and open new possibilities for knowledge discovery. 

Education:

• Ph.D. in Linguistics (Minor in Computer Science) - University of Minnesota, Twin Cities
• M.A. in Linguistics - University of Minnesota, Twin Cities
• B.S. in Educational Technology - Tianjin Foreign Studies University 

Teaching: 

IDS 2935 (Quest 2) - Fall 2024, Fall 2023: Making Sense: Understanding the World with Data and AI 

(Student presentation snaps)

GMS 5909 - Fall 2023, Fall 2022: Finding Biomedical Research Information and Communicating Science

Guest Lecture - PHC 3793 - Fall 2023, Fall 2022: Higher Thinking for Healthy Humans: AI in Healthcare and Public Health

Guest Lecture - BME 6938 - Spring 2023: Multimodal Data Mining

Library AI research award: 

Library Graduate Internship program 2023-2024: Collaborating with a UF graduate student intern and a faculty member from the Florida Museum of Natural History, we are leveraging Large Language Models (LLMs) and Computer Vision (CV) techniques to enhance the understanding and interpretation of natural history image collections.

Selected Publications: 

• Getting to Know Named Entity Recognition: Better Information Retrieval Med Ref Serv Q 2024
• Classifying early infant feeding status from clinical notes using natural language processing and machine learning Scientific Report, 2024 (co-author)
• Prompt Engineers or Librarians? An Exploration Med Ref Serv Q. 2023
• ChatGPT, an Opportunity to Understand More about Language Models Med Ref Serv Q. 2023 Apr-Jun; 42(2)
• Machine learning and natural language processing for classifying infant feeding status from clinical notes AMIA 2022 Annual Symposium (co-author)
• Shallow Parsing for Nepal Bhasa Complement Clauses In Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages, Association for Computational Linguistics. 2022 (co-author)
• The Multiple Mechanisms for Mandarin Sluices Proceedings of GLOW-in-Asia, 2019 (co-author)
• Embedding, Covert Movement, and Intervention in Newari In Proceedings of LSA 2018 (co-author)
• Entropy Reduction Prediction on Mandarin Chinese Relative Clauses Processdings of 2016 Buckeye East Asian Linguistics Forum 2
• Adverbial phrase placements in L1-Chinese ESL learners’ writing Linguistic Portfolios, 4(1), 9. 2015 (co-author)