@inproceedings{8a2de1b03c06462f98176d23e5fa16d3,
title = "Hindi-to-Urdu machine translation through transliteration",
abstract = "We present a novel approach to integrate transliteration into Hindi-to-Urdu statistical machine translation. We propose two probabilistic models, based on conditional and joint probability formulations, that are novel solutions to the problem. Our models consider both transliteration and translation when translating a particular Hindi word given the context whereas in previous work transliteration is only used for translating OOV (out-of-vocabulary) words. We use transliteration as a tool for disambiguation of Hindi homonyms which can be both translated or transliterated or transliterated differently based on different contexts. We obtain final BLEU scores of 19.35 (conditional probability model) and 19.00 (joint probability model) as compared to 14.30 for a baseline phrase-based system and 16.25 for a system which transliterates OOV words in the baseline system. This indicates that transliteration is useful for more than only translating OOV words for language pairs like Hindi-Urdu.",
author = "Nadir Durrani and Hassan Sajjad and Alexander Fraser and Helmut Schmid",
note = "Publisher Copyright: {\textcopyright} 2010 Association for Computational Linguistics.; 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 ; Conference date: 11-07-2010 Through 16-07-2010",
year = "2010",
language = "English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "465--474",
editor = "Jan Hajic and Sandra Carberry and Stephen Clark",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings",
address = "United States",
}