Naykhanov N.V., Dyshenov B.A. Computing semantic similarity of concepts using Wikipedia link

Abstract: The research question is the semantic relatedness of terms. The target of research is measure the semantic relatedness of terms. The authors consider such aspects as the rationale for the choice of the theme of background knowledge, the construction of a graph of links and measurement of relatedness between concepts. In earlier studies the authors of semantic proximity is calculated based on the statistical characteristics using different contextual analysis methods, such as latent semantic analysis. This work is the first experience with the reference methods for determining a semantic relatedness. Therefore, the focus placed on ease of calculation steps. Evaluation semantic similarity is based on the WLM method and proximity measure for separate types of references of M. I. Varlamov, A.V. Korshunov. In contrast to the well-known measures of semantic proximity, based on the use of Wikipedia proposed in the measure uses a simple links Wikipedia articles such as "See. Also" and "Links". This approach allows us to raise the performance of the algorithm and is designed for use in applications requiring high accuracy of the result is not, and better performance of the algorithm. These tasks include establishing a correspondence between the competencies and educational standard annotations disciplines of the curriculum or the task of analyzing the students' answers to the open questions in the form. The developed measure is cheap, reasonably accurate and accessible.

Keywords: