Enriching WordNet Ontology using Coarse - Grained Word Senses

All technologies have been emerged during the vision of Semantic Web are helpful for knowledge applications in various research areas. Semantic Web will consist of a distributed environment of shared and interoperable ontologies. Since building ontologies from scratch is not an easy task and is a time-consuming process, there is another perspective, which studies the approaches for developing and enriching ontologies either from reusing existing ontologies or from reusing different data sources. This paper presents a new approach that enriches WordNet based on Coarse-Grained word senses. These senses caused by applying WordNet Fine-Grained word senses to a Merging Sense algorithm. This algorithm merges only semantically similar word senses instead of applying traditional clustering techniques. Two different data sources are used in the enrichment process: Web documents and Corpus documents. The results obtained from using Coarse-Grained word senses yields better precision than Fine-Grained word senses in Word Sense Disambiguation task.