Building Ontologies to Understand Spoken Tunisian Dialect

TL;DR

This paper introduces an ontology-based method for understanding spoken Tunisian dialect, leveraging semantic concepts to improve comprehension without relying on extensive linguistic tools, tailored for dialogue systems.

Contribution

It presents a novel ontology construction approach for Tunisian dialect to enhance speech understanding in dialogue systems, addressing resource limitations.

Findings

Increased comprehension rate of Tunisian dialect speech.

Reduced dependence on linguistic processing tools.

Effective semantic annotation using ontologies.

Abstract

This paper presents a method to understand spoken Tunisian dialect based on lexical semantic. This method takes into account the specificity of the Tunisian dialect which has no linguistic processing tools. This method is ontology-based which allows exploiting the ontological concepts for semantic annotation and ontological relations for speech interpretation. This combination increases the rate of comprehension and limits the dependence on linguistic resources. This paper also details the process of building the ontology used for annotation and interpretation of Tunisian dialect in the context of speech understanding in dialogue systems for restricted domain.