Natural Language Processing / Information Extraction (NLP/IE) Program
The Natural Language Processing / Information Extraction (NLP/IE) Program (PIs: Genevieve Melton-Meaux, MD, MA and Serguei Pakhomov, PhD) at the University of Minnesota Institute for Health Informatics is a team of investigators, postdoctoral researchers, programmers, and students who work together on natural language processing (NLP) for a variety of clinical and biomedical tasks. We use NLP/IE to process, extract, and encode information from unstructured biomedical and clinical texts, including clinical texts from the electronic health record. These techniques are then leveraged to support the invention of new healthcare and research applications and the investigation of healthcare interventions.
Current active areas of NLP/IE research for our group include redundancy detection in clinical texts; biomedical semantic similarity and relatedness measures; acronym, abbreviation, and symbol disambiguation; semantic role labeling; automated monitoring of adverse drug events; language use patterns in patients with neurological diseases, tools for interoperability and integration of NLP systems, and specialized modules for different types of clinical texts. In addition, our group is developing an open-source biomedical and clinical UIMA-based NLP/IE pipeline application, BioMedICUS (BioMedical Information Collection and Understanding System), tailored for clinical and translational researchers. We have several NLP/IE resources related to our projects publicly available for other researchers.