Girish Sundaram
This is a likely match — the affiliation was inferred from OpenAlex, ORCID, and web sources but has not been fully confirmed. Treat with appropriate caution.
Role not yet determined Is this you? Add your title
Also affiliated: IBM (United States) (2010); Indian Institute of Technology Kharagpur (2016); IBM (India) (2011); Software602 (Czechia) (2013); Software (Spain) (2013)
Research Areas
Biography and Research Information
OverviewAI-generated summary
Girish Sundaram's research focuses on the application of natural language processing (NLP) and text mining techniques to automate systematic literature reviews. His work investigates methods for improving the efficiency and accuracy of information extraction from scientific literature, particularly in biomedical domains. Sundaram has explored the conversion of speech to structured data, such as SQL, and developed approaches for efficient indexing of large text datasets. His recent publications examine frameworks for measuring domain transfer in language embeddings and present a corpus derived from Randomized Controlled Trials (RCTs) to evaluate data versus vocabulary augmentation strategies for biomedical sequence labeling. He also co-authored work on parameter-efficient domain adaptation for biomedical text using embedding transfer. Sundaram has a publication record of 22 works, with an h-index of 3 and 44 citations.
Metrics
- h-index: 3
- Publications: 22
- Citations: 44
Selected Publications
-
Measuring Embedding-Level Domain Transfer: A Diagnostic Framework and a Caution Against Over-Reading Geometric Metrics (2026)
-
An RCT-Derived PICO Corpus and a Controlled Study of Data versus Vocabulary Augmentation for Biomedical Sequence Labeling (2026)
-
Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer (2026)
-
An RCT-Derived PICO Corpus and a Controlled Study of Data versus Vocabulary Augmentation for Biomedical Sequence Labeling (2026)
-
Loss-Function Strategies for Severe Class Imbalance in Biomedical Token Classication: Weighted Cross-Entropy, Manual Weighting, and Focal Loss (2026)
-
Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer (2026)
-
Loss-Function Strategies for Severe Class Imbalance in Biomedical Token Classication: Weighted Cross-Entropy, Manual Weighting, and Focal Loss (2026)
-
Benchmarking Domain-Specic, General-Purpose, and BLURB Models for PICO Classication Under Severe Class Imbalance (2026)
-
Measuring Embedding-Level Domain Transfer: A Diagnostic Framework and a Caution Against Over-Reading Geometric Metrics (2026)
-
Benchmarking Domain-Specic, General-Purpose, and BLURB Models for PICO Classication Under Severe Class Imbalance (2026)
-
Benchmarking Domain-Specific, General-Purpose, and BLURB Models for PICO Classification Under Severe Class Imbalance (2026)
-
Measuring Embedding-Level Domain Transfer: A Diagnostic Framework and a Caution Against Over-Reading Geometric Metrics (2026)
-
Loss-Function Strategies for Severe Class Imbalance in Biomedical Token Classication: Weighted Cross-Entropy, Manual Weighting, and Focal Loss (2026)
-
Automating Systematic Literature Reviews with Natural Language Processing and Text Mining: A Systematic Literature Review (2023)
Collaboration Network
Top Collaborators
- Automating Systematic Literature Reviews with Natural Language Processing and Text Mining: A Systematic Literature Review
- Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer
Similar Researchers
Based on overlapping research topics