Automatic Extraction of Ontology Relations From Medical Abstracts

Authors

  • Jin-Cheon Na Nanyang Technological University, Singapore
  • Christopher Khoo Nanyang Technological University, Singapore
  • Chew-Hung Lee Nanyang Technological University, Singapore
  • Chew-Hung Lee Nanyang Technological University, Singapore

DOI:

https://doi.org/10.7152/acro.v14i1.14112

Abstract

Ontologies play an important role in the Semantic Web as well as in knowledge management. This project seeks to develop an automatic method to build ontologies, especially in a medical domain. The initial study investigates an approach of identifying pairs of related concepts using association rule induction and identifying semantic relations between concepts using an existing medical knowledge base, the UMLS (Unified Medical Language System) semantic net. This is evaluated by comparing the result with manually assigned semantic relations based on an analysis of medical abstracts containing each pair of concepts. Our initial finding shows that the automatic process is promising, achieving a 68% coverage compared to manual tagging. We also discuss about probable approaches for the improvement of the identification of semantic relations by employing natural language processing techniques.

Downloads

Published

2003-10-01