Retrieval of semantic concepts based on analysis of texts for automatic construction of ontology

Citation

Krishnan R, Hussain A & Sherimon PC (2012) Retrieval of semantic concepts based on analysis of texts for automatic construction of ontology. In: Huang T, Zeng Z, Li C & Leung C (eds.) Neural Information Processing: 19th International Conference, ICONIP 2012, Doha, Qatar, November 12-15, 2012, Proceedings, Part I. Lecture Notes in Computer Science, 7663. Berlin Heidelberg: Springer, pp. 524-532. http://link.springer.com/chapter/10.1007/978-3-642-34475-6_63#

Abstract
Ontology together with Semantic Web has a vital role in knowledge management on a global scale. Since manual construction of ontology leads to complex, time consuming and inconsistent results, automatic construction of ontology is more preferred. This consists of two phases, such as concept based retrieval and the generation of ontology. The extraction of the semantic concept from unstructured input document is focused in this paper. Semantic concepts can be extracted based on the analysis of a set of texts and using WordNet. Challenges facing are finding of semantic relationships among concepts and elimination of irrelevant documents by identifying conceptual mismatches. For each word in the text document, corresponding synonym, hyponym, and hypernym will be extracted from the WordNet. These concepts and their relationships can be used to make the taxonomy for the automatic construction of ontology. JDK and Net Beans IDE are used with WordNet for the implementation.

Keywords
Ontology; Semantic Web; Automatic Ontology Construction; WordNet; Synonym; Hyponym; Hypernym