Odia transliteration engine using moses

Author

Balabantaray, R.C. ; Sahoo, D.

Author_Institution

Dept. Oof CSE, IIIT Bhubaneswar, Bhubaneswar, India

fYear

2014

fDate

9-11 Jan. 2014

Firstpage

27

Lastpage

29

Abstract

Transliteration is an important Natural Language Processing task. Transliteration is an automatic method for converting words in one language into phonetically equivalent ones in another language. In this paper we use the popular phrase-based SMT techniques for the task of machine transliteration, for Odia-English and Odia-Hindi language pair. We have created two models for syllable based splits (Odia-English, Odia-Hindi) on 50,900 parallel entries and two models for character based splits (Odia-English, Odia-Hindi) on 1,10,000 parallel entries. SRILM is used to build statistical language models. GIZA++ is used to perform word alignments over parallel corpora. We have achieved an accuracy of 89% for Odia-English and 86% for Odia-Hindi on Syllable based split and 71% for Odia-English and 85% for Odia-Hindi on character based split.

Keywords

language translation; natural language processing; GIZA++; Moses; Odia transliteration engine; Odia-English language pair; Odia-Hindi language pair; SRILM; character based splits; machine transliteration; natural language processing; phrase-based SMT techniques; statistical language models; syllable based splits; Accuracy; Computational modeling; Dynamic programming; Media; Programming; RNA; Character based split; GIZA++; SRILM; Syllable based split; corpus; moses;

fLanguage

English

Publisher

ieee

Conference_Titel

Business and Information Management (ICBIM), 2014 2nd International Conference on

Conference_Location

Durgapur

Print_ISBN

978-1-4799-3263-4

Type

conf

DOI

10.1109/ICBIM.2014.6970927

Filename

6970927