An Information Extraction Approach for Building Vocabulary and Domain Specific Ontology in Information Technology
Ta Cong Duy Chien, Phan Thị Tươi · Research and Development on Information and Communication Technology · 2014
This paper introduces the HETEONTO system that extracts concepts from text files and existing ontologies such as Wikipedia, ACM, and WordNet in order to build the vocabulary and domain specific ontology focusing on Information Technology domain. It also describes how to import concepts into domain ontology. Data sources and techniques deployed in HETEONTO for ontology learning from texts, Wikipedia, WordNet are briefly presented herein. This paper then focuses on evaluating the generated domain ontology by selected methods. One of these methods that we introduce here, is comparative. Comparative evaluation performed in this study use the same corpus to contrast result from HETEONTO. Results generated by such experiments show that HETEONTO yields superior performance, especially regarding semantic relation