Semantic Interpretation of Medical Language - Quantitative Analysis and Qualitative Yield
We report on results from an empirical analysis of the semantic interpretation of medical free texts. Our approach to semantic interpretation is based on a lean collection of interpretation rules which are triggered by well-defined configurations in dependency graphs in order to compute a conceptual representation of the texts’ contents. We evaluate the accuracy of semantic interpretation for three types of syntactic dependency patterns, viz. genitives, auxiliary and modal verb complexes, and prepositional phrases. Besides quantitative considerations, we focus on the heuristic guidance, as provided by patterns underlying the semantic interpretation of prepositional phrases, for monitoring the quality of the medical domain knowledge base.
KeywordsLamina Propria Conceptual Relation Dependency Graph Medical Informatics Content Word
Unable to display preview. Download preview PDF.
- 1.C. Friedman and G. Hripcsak. Evaluating natural language processors in the clinical domain. Methods of Information in Medicine, 37(4/5):334–344, 1998.Google Scholar
- 3.U. Hahn, M. Romacker, and St. Schulz. MEDSynDiKATe: Design considerations for an ontology-based medical text understanding system. In J. M. Overhage, editor, AMIA 2000 — Proc. of the Annual Symposium of the American Medical Informatics Association, pages 330–334. Los Angeles, CA, November 4–8, 2000. Philadelphia, PA: Hanley & Belfus, 2000.Google Scholar
- 4.G. Hripcsak, C. Friedman, P. Alderson, W. DuMouchel, S. Johnson, and PD. Clayton. Unlocking clinical data from narrative reports: a study of natural language processing. Annals of Internal Medicine, 122(9):681–688, 1995.Google Scholar
- 5.R. Klar, A. Zaiß, A. Timmermann, and U. Schrader. The information system of the Freiburger University Hospital. In K. Adlassnig et al., editor, MIE’91 — Proceedings of the Medical Informatics Europe 1991, pages 46–50. Berlin: Springer, 1991.Google Scholar
- 6.A. Nazarenko, P. Zweigenbaum, J. Bouaud, and B. Habert. Corpus-based identification and refinement of semantic classes. In R. Masys, editor, AMIA’97 — Proc. of the 1997 AMIA Annual Fall Symposium (formerly SCAMC), pages 585–589. Philadelphia, PA: Hanley & Belfus, 1997.Google Scholar
- 7.A. Rector, D. Solomon, W. Nowlan, and T. Rush. A terminology server for medical language and medical information systems. Methods of Information in Medicine, 34(2):147–157, 1995.Google Scholar
- 8.M. Romacker, St. Schulz, and U. Hahn. Small is beautiful: Compact semantics for medical language processing. In W. Horn, Y. Shahar, G. Lindberg, S. Andreassen, and J. Wyatt, editors, AIMDM’99 — Proc. of the Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making, pages 400–410. Berlin: Springer, 1999.Google Scholar
- 9.S. Siegel and J. Castellan. Nonparametric statistics for the behavioral sciences. New York: McGraw-Hill, 2 edition, 1988.Google Scholar
- 11.P. Zweigenbaum, J. Bouaud, B. Bachimont, J. Charlet, and J.-F. Boisvieux. Evaluating a normalized conceptual representation produced from natural language patient discharge summaries. In R. Masys, editor, AMIA’97 — Proc. of the 1997 AMIA Annual Fall Symposium (formerly SCAMC), pages 590–594. Philadelphia, PA: Hanley & Belfus, 1997.Google Scholar