Word Similarity Algorithm Based on WordNet And HowNet

To make the word similarity calculated results more reasonable and accurate, a new word similarity algorithm is proposed. It uses How Net primitive hierarchical tree structure, and calculates the two primitives' distance with the method computing Word Net node distance which considers the tree depth, density, path and connecting intensity, etc. Moreover, algorithm also improves the method that distance into similarity. Finally, this algorithm is compared with related algorithms through experiment. The results show that the proposed algorithm effectively improves the precision and accuracy of word similarity calculation.