Dependency resolution and semantic mining using Tree Adjoining Grammars for Tamil Language

TL;DR

This paper explores using Tree Adjoining Grammars (TAGs) to model Tamil syntax and semantics, demonstrating dependency resolution and semantic mining through parsing Tamil sentences with a custom TAG parser.

Contribution

It presents the first application of TAGs to Tamil language syntax and semantics, including dependency resolution and semantic mining without relying on statistical methods.

Findings

Successfully modeled Tamil syntax with TAGs

Demonstrated semantic mining via dependency resolution

Developed a custom TAG parser for Tamil sentences

Abstract

Tree adjoining grammars (TAGs) provide an ample tool to capture syntax of many Indian languages. Tamil represents a special challenge to computational formalisms as it has extensive agglutinative morphology and a comparatively difficult argument structure. Modelling Tamil syntax and morphology using TAG is an interesting problem which has not been in focus even though TAGs are over 4 decades old, since its inception. Our research with Tamil TAGs have shown us that we can not only represent syntax of the language, but to an extent mine out semantics through dependency resolution of the sentence. But in order to demonstrate this phenomenal property, we need to parse Tamil language sentences using TAGs we have built and through parsing obtain a derivation we could use to resolve dependencies, thus proving the semantic property. We use an in-house developed pseudo lexical TAG chart parser; algorithm given by Schabes and Joshi (1988), for generating derivations of sentences. We do not use any statistics to rank out ambiguous derivations but rather use all of them to understand the mentioned semantic relation with in TAGs for Tamil. We shall also present a brief parser analysis for the completeness of our discussions.