Some Strategies to Capture Karaka-Yogyata with Special Reference to apadana

TL;DR

This paper explores computational methods to determine word compatibility (Yogyat ext= a) for disambiguation in Sanskrit texts, utilizing Indian philosophical theories and creating an ontological tagging system.

Contribution

It introduces a novel approach combining Ny ext=aya and Vy ext=akarana theories to develop a tool for capturing Yogyat ext= a in computational linguistics.

Findings

Proposed a method for resolving ambiguity using Yogyat ext= a

Developed an ontological tag-set for Sanskrit lexicon

Presented case studies demonstrating the approach

Abstract

In today's digital world language technology has gained importance. Several softwares, have been developed and are available in the field of computational linguistics. Such tools play a crucial role in making classical language texts easily accessible. Some Indian philosophical schools have contributed towards various techniques of verbal cognition to analyze sentences correctly. These theories can be used to build computational tools for word sense disambiguation (WSD). In the absence of WSD, one cannot have proper verbal cognition. These theories considered the concept of 'Yogyat\=a' (congruity or compatibility) as the indispensable cause of verbal cognition. In this work, we come up with some insights on the basis of these theories to create a tool that will capture Yogyat\=a of words. We describe the problem of ambiguity in a text and present a method to resolve it computationally with the help of Yogyat\=a. Here, only two major schools i.e. Ny\=aya and Vy\=akarana are considered. Our paper attempts to show the implication of the creation of our tool in this area. Also, our tool involves the creation of an 'ontological tag-set' as well as strategies to mark up the lexicon. The introductory description of ablation is also covered in this paper. Such strategies and some case studies shall form the core of our paper.