Text similarity measures have been widely studied and used in machine learning and information retrieval for many years. However, few applications of text similarity have dealt with multi-lingual translations of a specific document. Additionally, the growing number of texts with more translations being generated increases the challenge of distinguishing or identifying the similarity and differences between texts across different documents. In this article, we employ different text similarity measures to delve into the problem of text similarity in the context of multi-lingual representations of the Qur'an. Four semantic translations of the Qur'an are used for comparative study and analysis. We compare and contrast the effect of applying five similarity measures across these representations. We analyze the results along two classes namely: identical verse pairs and similar verse pairs. Our analysis provides helpful observations about the impact of the five distance metrics for verse similarity in the Qur'an across different languages.
展开▼
