Objectives : Postpositional Parser and Analyzer is a program which compiles and analyses pronouns of Telugu language into their roots and their constituent postpositions along with their grammatical properties, which is a full length translation surface of Telugu Pronouns . Grammatical properties at word level includes finding a tense, number, gender , person and other associated features. Methods :The method employed in this paper is based on Suffix-Order-Pattern technique to develop a computational model for morphological analysis of pronouns in Telugu. Suffix-Order-Pattern is a new technique in linguistic computation. The current work is a module of a POS Tagger and Word-Level translation surface for Telugu, a java application developed for analyzing Telugu pronouns. Test samples were taken from grammar text books for Telugu language and tested thoroughly with various inflections of pronouns with respect to tense, person, number and gender. Findings: The evaluation was performed on a data set taken from Wiktionary (Wiktionary is a multilingual, Web-based project to create a free content dictionary, available in over 150 languages). The results were very encouraging as the accuracy of the developed software is really absolute. The findings cannot be compared with any other results published because very little work was done previously in this area of research in Telugu language. Application/Improvements: The procedure used to build this is theoretically justified and practically executed for variety of inflections related to Telugu pronouns . The present proposal is a demonstration of XML based repository for all the root words of different categories of Telugu Pronouns. It is an optimal organization of linguistic database and its performance in computational environment is highly motivated.
展开▼
