Philip Ogren

I am a computer scientist living and working in Boulder, CO. In December 2010 I successfully defended my PhD dissertation in Computer Science and will graduate in May of 2011 from the University of Colorado at Boulder. My dissertation topic focused on syntactic coordination resolution in the biomedical domain using machine learning and language modeling. I enjoy working on open source solutions for natural language processing tasks and am a primary contributor to four projects: ClearTK, uimaFIT, Biomedicus, and Knowtator. I have worked on a variety of challenging problems related to syntactic analysis, information extraction, information retrieval, and text classification. These include syntactic coordination, named entity recognition, searching of controlled vocabularies (e.g. SNOMED-CT), chat classification, and e-mail structure analysis, among others. I have rendered consulting services to a variety of academic and industry clients in the biomedical, technology, and legal domains providing production-level code that has been incorporated into commercial products and open-source code that enables research. I am an active participant in the Biomedical Text Mining Group at the Center for Computational Pharmacology at the University of Colorado Denver at the Anschutz Medical Campus. I also work with the Center for Computational Language and EducAtion Research at the University of Colorado at Boulder.

Contact Information

• email: philip@ogren.info
• phone: (720) 563-7679
• academic webpage
• resume available upon request

Software

• ClearTK - a framework for building natural language processing (NLP) components that make use of machine learning algorithms as a foundation for decision making and annotation creation. ClearTK is built on top of UIMA.
• uimaFIT - provides factories, injection, and testing utilities for UIMA components.
• Biomedicus - leverages open source solutions for text analysis and provides new analytic tools for processing and analyzing text of clinical reports.
• Knowtator - a general-purpose text annotation tool that is integrated with the Protégé knowledge representation system.
• cTAKES - (secondary contributor) cTAKES processes clinical notes and identifies types of clinical named entities – drugs, diseases/disorders, signs/symptoms, anatomical sites and procedures.

Work History/Timeline

Education

• PhD, Computer Science, University of Colorado at Boulder, expected graduation date: May 2011
• Master of Science, Computer Science, University of Colorado at Boulder, May 2005
• Bachelor of Science, Mathematics, Harding University, December 1997

Publications