A Comparison of Semantic Similarity Methods for Maximum Human Interpretability
This work addresses the need for interpretable similarity measures in information retrieval applications, but it is incremental as it compares existing methods on a specific dataset.
The paper tackled the problem of improving semantic similarity measures for better human interpretability by comparing three methods that incorporate semantic information, finding that cosine similarity using tf-idf vectors performed best on short news texts.
The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable results for further analysis. The similarity calculation method that focuses on features related to the text's words only, will give less accurate results. This paper presents three different methods that not only focus on the text's words but also incorporates semantic information of texts in their feature vector and computes semantic similarities. These methods are based on corpus-based and knowledge-based methods, which are: cosine similarity using tf-idf vectors, cosine similarity using word embedding and soft cosine similarity using word embedding. Among these three, cosine similarity using tf-idf vectors performed best in finding similarities between short news texts. The similar texts given by the method are easy to interpret and can be used directly in other information retrieval applications.