Parsing Techniques using Paninian Framework on Nepali Language

Abstract

This paper presents three parsing techniques for establishing karaka-vibhakti relations using Paninian framework for nepali language. It uses the concept of karaka relation between verbs and nouns in the sentence. The constraints problem reduces to bipartite graph matching problem because of the nature of constraints and bipartite graph reduces to hopfield network. Upon employing these three techniques viz. constraint based , bipartite graph matching problem and hopfield networks using the Paninial framework to the sentences of nepali language an elegant account of the relation between surface form (vibhakti) and semantic (karaka) roles is obtained. All the three techniques are demonstrated by forming parsing structure in various nepali sentences.