A Connectionist Approach to Learn Marathi Language

Author

Kolhe, S.R. ; Pawar, B.V.

Author_Institution

North Maharashtra Univ., Jalgaon

fYear

2008

fDate

16-18 July 2008

Firstpage

1222

Lastpage

1227

Abstract

In this paper, we have investigated the inductive inference of complex grammar of subset of Marathi (Indian) language and results are reported. We have investigated Elman recurrent networks (ERNs), Jordon recurrent networks (JRNs), time lagged recurrent networks (TLRNs) and recurrent neural networks (RNNs). In this empirical study, we consider the task of classifying Marathi language sentences as grammatical or ungrammatical as well as modeled the problem as a prediction problem. We have also analyzed the operation of the networks by investing rule approximation.

Keywords

grammars; learning (artificial intelligence); natural language processing; recurrent neural nets; Elman recurrent network; Jordon recurrent network; Marathi language learning; complex grammar; connectionist approach; inductive inference; recurrent neural network; rule approximation; sentence classification; time lagged recurrent network; Artificial neural networks; Backpropagation; Computer science; Encoding; Natural language processing; Natural languages; Neural networks; Predictive models; Recurrent neural networks; Speech; Language processing; Neural networks; Neurolinguistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Trends in Engineering and Technology, 2008. ICETET '08. First International Conference on

Conference_Location

Nagpur, Maharashtra

Print_ISBN

978-0-7695-3267-7

Electronic_ISBN

978-0-7695-3267-7

Type

conf

DOI

10.1109/ICETET.2008.15

Filename

4580091