Transfer Grammar in Tamil-Hindi MT System

Author

Devi, Sobha Lalitha ; Gopalan, Sindhuja ; Ram, V.S.

Author_Institution

AU-KBC Res. Centre, Anna Univ., Chennai, India

fYear

2013

fDate

17-19 Aug. 2013

Firstpage

79

Lastpage

82

Abstract

In this paper, we present the work on transfer grammar, one of the most challenging issues in MT, in a bidirectional Tamil-Hindi translation system-Sam park. Transfer grammar between the above languages can be categorized into two levels (1) the structure transfer and (2) lexical level transfer. Tamil and Hindi differ extensively at the clausal construction level and at the verb formation level since Tamil is an agglutinative language and Hindi is not. Transfer grammar described here uses a hybrid approach using CRF a machine learning algorithm and linguistic rules for structure transfer, a rule based approach for word level transfer. We tested the approach in the Sam park system using web data and the results are encouraging.

Keywords

Internet; computational linguistics; grammars; learning (artificial intelligence); natural language processing; Sampark; Tamil-Hindi MT system; Web data; bidirectional Tamil-Hindi translation system; lexical level transfer; linguistic rules; machine learning algorithm; structure transfer; transfer grammar; Accuracy; Compounds; Computational linguistics; Grammar; Random access memory; Semantics; Syntactics; Tamil-Hindi MT; syntactic structure transfer; transfer grammar; word level transfer;

fLanguage

English

Publisher

ieee

Conference_Titel

Asian Language Processing (IALP), 2013 International Conference on

Conference_Location

Urumqi

Type

conf

DOI

10.1109/IALP.2013.24

Filename

6646008