Principled disambiguation: discriminating adjective senses with modified nouns
Computational Linguistics
A fast string searching algorithm
Communications of the ACM
Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites
Computational Linguistics
Brief communication: Retrieving definitional content for ontology development
Computational Biology and Chemistry
Text2Onto: a framework for ontology learning and data-driven change discovery
NLDB'05 Proceedings of the 10th international conference on Natural Language Processing and Information Systems
Guest Editorial: Current issues in biomedical text mining and natural language processing
Journal of Biomedical Informatics
A clustering study of a 7000 EU document inventory using MDS and SOM
Expert Systems with Applications: An International Journal
Extracting significant Website Key Objects: A Semantic Web mining approach
Engineering Applications of Artificial Intelligence
Hi-index | 0.00 |
Developing ontologies to account for the complexity of biological systems requires the time intensive collaboration of many participants with expertise in various fields. While each participant may contribute to construct a list of terms for ontology development, no objective methods have been developed to evaluate how relevant each of these terms is to the intended domain. We have developed a computational method based on a hypergeometric enrichment test to evaluate the relevance of such terms to the intended domain. The proposed method uses the PubMed literature database to evaluate whether each potential term for ontology development is overrepresented in the abstracts that discuss the particular domain. This evaluation provides an objective approach to assess terms and prioritize them for ontology development.