Word Sense Disambiguation string semantic similarity business process model similarity
Similarity value calculation between business process model has an important role in managing the business process model repository. One of its uses is to facilitate searching process of a model in the repository. Similarity value calculation of business processes is closely related with semantic string similarity. Semantic string similarity is usually performed by utilizing a lexical database such as WordNet to find the semantic meaning of the word. Problems arise when WordNet contains terms that have more than one meaning or polysemous. False selection will cause a decrease in the accuracy of similarity calculation process. In this study, we will try to improve the accuracy of similarity calculation of business processes using Word Sense Disambiguation (WSD) process. The purpose is to eliminate the ambiguity of polysemous words before similarity value calculation process. WSD is performed using unsupervised methods by looking at the value of graph connectivity. The lexical data base used is a database that is focused on the words in business and industry field. Results from this study achieved higher accuracy in the process of meaning selection especially to the terms related to business and industrial domains. This will also increasing the accuracy in similarity value calculation between the business process models.