Title: Domain Ontology Building Process Based on Text Mining from Medical Structured Corpus

Year of Publication: Jan - 2015
Page Numbers: 128-139
Authors: Driouche Razika, Bensassi Houda and Kemcha Nawel
Conference Name: The International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC2015)
- United Arab Emirates

Abstract:


Ontologies have become an important means for structuring knowledge and building knowledgeintensive systems. With the advent of ontologies being used in many different fields of computer science, developing appropriate methods to automate ontology engineering become an increasingly important goal. For this purpose, efforts have been made to facilitate the ontology engineering process, in particular the construction of ontology from domain texts. Hence, we present an extraction and building process to generate and evaluate domain ontology using text-mining techniques. We exploit domain specific texts collected from medical reports in order to automatically extract terms. These terms are sets of concepts/relations which have either taxonomic or non-taxonomic relationships among them. We have developed an extensive and detailed ontology in the field of gynaecology using this process.