COMPUTATIONAL TOOL FOR SANSKRIT SAMASA ANALYSIS: A STEP TOWARDS PRESERVING AND NOURISHING SANSKRIT TEXTS

Abstract

Sanskrit language has played a crucial role in communicating the unbroken knowledge tradition of the Indian intellectual tradition from the Vedic times to the present. The language is a treasure trove of information, but it is being threatened by the lack of a systematic approach for preserving and nourishing the texts. The sheer volume and variety of data require a good amount of computerization, and a networked approach across centers is necessary for data exchange in real-time. In this regard, the development of a computational tool for Sanskrit Samasa Analysis is essential. Sanskrit language has been analyzed by Shastric Scholars without the stage called "Part of Speech" (POS). The whole process involves many steps, but it does not stress upon POS analysis. However, the development of a computational tool for Samasa Analysis is important as it helps in automatic translation from Sanskrit to Indian languages, which is highly desirable. The computational tool will be a semi-automatic system and will use a human being's knowledge about the world to take a decision about which analysis is correct. The tool will help scholars in word-split, Markup for Sandhi, and Samasa analysis. This paper presents the methodology for developing a computational tool for Sanskrit Samasa Analysis. The paper highlights the need for the tool and the methodology used for its development. The paper discusses how the tool will use a semi-automatic system towards the end, and not all scholars creating content need to be engaged in this. The paper also discusses how the tool will be online and can be accessed at any time.