Improve word sense disambiguation by proposing a pruning method for optimizing conceptual density´s contexts

In this paper, the role of nouns in reducing the conceptual density of contexts has been examined. A new method is proposed to identify and prune nouns with negative impact on conceptual density of contexts. In the proposed method, a fitness function is offered; a fitness degree is assigned to unambiguous nouns sense within the context. Using the mean fitness degree of unambiguous nouns´ sense, a threshold is produced for that context. This threshold is then used as a measure to prune the sense of nouns with lower fitness degree that reduces the conceptual density of the context. Finally, by implementing this method on the contexts produced by conceptual density method, all contexts will be optimized significantly; this significantly increases the accuracy of disambiguation.