CLApr 5, 2016

A new TAG Formalism for Tamil and Parser Analytics

arXiv:1604.01235v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of parsing Tamil for computational linguistics, but it is incremental as it builds on existing TAG formalisms without major breakthroughs.

The authors tackled the challenge of designing a Tree Adjoining Grammar (TAG) for Tamil, a morphologically rich language, by presenting a minimalistic TAG without extensive morphological considerations and implementing a parser with variations from the XTAG system.

Tree adjoining grammar (TAG) is specifically suited for morph rich and agglutinated languages like Tamil due to its psycho linguistic features and parse time dependency and morph resolution. Though TAG and LTAG formalisms have been known for about 3 decades, efforts on designing TAG Syntax for Tamil have not been entirely successful due to the complexity of its specification and the rich morphology of Tamil language. In this paper we present a minimalistic TAG for Tamil without much morphological considerations and also introduce a parser implementation with some obvious variations from the XTAG system

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes