NLM’s natural language processing (NLP), or text mining, research focuses on the development and evaluation of computer algorithms for automated text analysis. This area of research works primarily with text from the biomedical literature or electronic medical records and examines a wide variety of NLP tasks, including information extraction, literature searches, question answering, and text summarization.
Tenure Track Investigator, Computational Health Research Branch
Dina Demner-Fushman, MD, PhD
- Investigating biomedical question answering
- Developing the InfoBOT clinical decision support system (at the NIH Clinical Center)
- Leading the Consumer Health Question Answering project, which supports finding answers, in MedlinePlus and other reliable sources, to consumer questions received by NLM
- Participating in the Visual Question Answering task, which seeks to answer questions about the contents of medical images
Senior Investigator, Computational Biology Branch
Zhiyong Lu, PhD
- Exploring the use of NLP in support of literature search and curation
- Investigating the use of NLP for improving NLM PubMed search and indexing (e.g., the Best Match feature)
- Developing full-text literature mining and information extraction for curation at scale (e.g., NLM PubTator Central)
- Extracting genotype-phenotype relationships to assist with variant interpretation and precision medicine (e.g., NLM LitVar)
