Semantic Similarity Based on Word Recurrence Ratio Focusing on WordNet

Some texts can convey the same meaning without consisting of common words because of the distinct ramification of sentences. Thence traditional string overlapping is not enough for measuring the semantic similarity. For the acquirement of semantic textual similarity, the word semantics and their senses should be considered. In this paper, we proposed a ratio considering words overlapping. The ratio is calculated in terms of common words and the uncommon words of two texts. We employed WordNet components to estimate semantic similarity. Various existing WordNet measures emphasize different relationships and information of words in a taxonomy. We used three prominent WordNet measures. With the procedure we applied on WordNet measures, they are individually not susceptible enough to the criterion of sentence similarity approximation. Therefore, based on the ratio, we dynamically choose several combinations of WordNet measures to capture the semantic similarity. To validate our proposed method, we conduct several experiments on the SemEval STS dataset. The experimental result revealed that our proposed method shows an efficient p erformance and outperformed some known related methods in terms of different evaluation metrics.