Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu)

TL;DR

This paper explores automating the identification of sense-types of Telugu verbs in OntoSenseNet using classifiers, demonstrating effective enrichment with SVM and Adaboost.

Contribution

It introduces a method to automate sense-type tagging of Telugu verbs, enhancing OntoSenseNet for future linguistic research.

Findings

SVM classifiers effectively automate sense-type identification.

Adaboost ensemble improves tagging accuracy.

Automated enrichment enhances resource utility.

Abstract

In this paper, we discuss the enrichment of a manually developed resource of Telugu lexicon, OntoSenseNet. OntoSenseNet is a ontological sense annotated lexicon that marks each verb of Telugu with a primary and a secondary sense. The area of research is relatively recent but has a large scope of development. We provide an introductory work to enrich the OntoSenseNet to promote further research in Telugu. Classifiers are adopted to learn the sense relevant features of the words in the resource and also to automate the tagging of sense-types for verbs. We perform a comparative analysis of different classifiers applied on OntoSenseNet. The results of the experiment prove that automated enrichment of the resource is effective using SVM classifiers and Adaboost ensemble.