Document Details

Document Type : Article In Conference 
Document Title :
A Hybrid Model for Urdu Hindi Transliteration
نموذج هجين للتمثيل الصوتي للغتين الهندية والأوردية
 
Subject : transliteration of Urdu and Hindi 
Document Language : English 
Abstract : We report in this paper a novel hybrid approach for Urdu to Hindi transliteration that combines finite-state machine (FSM) based techniques with statistical word language model based approach. The output from the FSM is filtered with the word language model to produce the correct Hindi output. The main problem handled is the case of omission of diacritical marks from the input Urdu text. Our system produces the correct Hindi output even when the crucial information in the form of diacritic marks is absent. The approach improves the accuracy of the transducer-only approach from 50.7% to 79.1%. The results reported show that performance can be improved using a word language model to disambiguate the output produced by the transducer-only approach, especially when diacritic marks are not present in the Urdu input. 
Conference Name : Named Entities Workshop: Joint Conference the 47th Annual Meeting of the Association of Computational Linguistics (ACL) and the 4th International Join 
Duration : From : 00 AH - To : 00 AH
From : 00 AD - To : 00 AD 
Publishing Year : 1430 AH
2009 AD 
Number Of Pages : 00 
Article Type : Article 
Conference Place : Translation, transliteration, Urdu, Hindi 
Added Date : Wednesday, June 27, 2012 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
محمد غلام مالكMalik, Muhammad GhulamInvestigator mgmalik@kau.edu.sa
Lurent BesacierBesacier, Lurent Researcher Laurent.Besacier@imag.fr
Christian BoitetBoitet, Christian Researcher Christian.Boitet@imag.fr
Pushpak BhattcharyyaBhattcharyya, Pushpak Researcher pb@cse.iitb.ac.in

Files

File NameTypeDescription
 33809.pdf pdf 

Back To Researches Page