Bipasha Banerjee

About

I am an Assistant Professor at Virginia Tech, where I currently work as an AI Research Scientist, Digital Libraries for the University Library.

I completed my Ph.D. from Virginia Tech in July 2024. My dissertation titled "Improving Access to ETD Elements Through Chapter Categorization and Summarization" brings computational access to long documents such as Electronic Theses and Dissertations (ETDs) by providing readers with more granular level metadata information such as chapter summaries and classification labels.

Employment

• Virginia Tech AI Research Scientist, Digital Libraries, Assistant Professor
  2024 - Present
• Virginia Tech Graduate Research Assistant
  2019 - 2024
• Automatic Data Processing (United States) Global Product and Techonology Intern
  2019 - 2019
• Virginia Tech Graduate Teaching Assistant
  2019 - 2019

Education

• Virginia Tech PhD
  2019 - 2024
• Virginia Tech Master of Science (MS)
  ? - 2022
• Institute of Engineering & Management Bachelor of Technology (BTech)
  ? - 2015

Projects & Funding

Projects & funding information is unavailable.

Publications (16)

• Evaluating Human-LLM Alignment in ETD Subject Classification
  2026 DOI: 10.1007/978-3-032-06136-2_6
  +Save
• Context-Based URL Classification for Open Access Datasets and Software in Scholarly Documents
  2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL) 2025 DOI: 10.1109/jcdl67857.2025.00031
  +Save
• Learning from LLM Disagreement in Retrieval Evaluation
  2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL) 2025 DOI: 10.1109/jcdl67857.2025.00024
  +Save
• Retrieval-Augmented LLMs for ETD Subject Classification
  2025 DOI: 10.1109/BigData66926.2025.11402222
  +Save
• Using an Ensemble Approach for Layout Detection and Extraction from Historical Newspapers
  2025 DOI: 10.1109/BigData66926.2025.11401834
  +Save
• Optical Character Recognition for Pre-Digital Historical Documents using Large Language Models
  IEEE 24th International Conference on Machine Learning and Applications 2025
  +Save
• Using an Ensemble Approach for Layout Detection and Extraction from Historical Newspapers
  2025 IEEE BigData 2025
  +Save
• Agentic AI for Improving Precision in Identifying Contributions to Sustainable Development Goals
  2024 IEEE International Conference on Big Data (BigData) 2024 DOI: 10.1109/bigdata62323.2024.10825072
  +Save
• Automating Chapter-Level Classification for Electronic Theses and Dissertations
  2024 IEEE International Conference on Big Data (BigData) 2024 DOI: 10.1109/bigdata62323.2024.10825418
  +Save
• Making History Readable
  2024 IEEE International Conference on Big Data (BigData) 2024 DOI: 10.1109/bigdata62323.2024.10826028
  +Save