Building Information Extraction System Based on Computing Domain Ontology

Abstract

In this paper, we present an Information Extraction (IE) system, which is built from unstructured text based on Computing domain ontology. The IE system comprises four sequential processing steps: preprocessing, topic identifier, building domain specific ontology and extracting information from text corpus. The first two steps perform generic Natural Language Processing (NLP) and Machine Learning tasks, while the last two phases are application-specific and require a thorough understanding of the application domain. Furthermore, the paper focuses on evaluating the IE IEsystem by selected methods. One of these methods that we introduced here, is comparative. Comparative evaluation performed in this study use of Key Exchange Algorithm with the same corpus to contrast results. Results generated by such experiments show that this IE system outperforms Key Exchange Algorithm, respectably.