A Punjabi to Hindi Machine Transliteration System

Gurpreet Singh Josan ； Gurpreet Singh Lehal

《中文計算語言學期刊》 15卷2期 (2010/06) Pp. 77-102

https://doi.org/10.30019/IJCLCLP.201006.0001

並列摘要

Transliteration is the general choice for handling named entities and out of vocabulary words in any MT application, particularly in machine translation. Transliteration (or forward transliteration) is the process of mapping source language phonemes or graphemes into target language approximations; the reverse process is called back transliteration. This paper presents a novel approach to improve Punjabi to Hindi transliteration by combining a basic character to character mapping approach with rule based and Soundex based enhancements. Experimental results show that our approach effectively improves the word accuracy rate and average Levenshtein distance of the various categories by a large margin.

並列關鍵字

Transliteration ； Punjabi ； Hindi ； Soundex Approach ； Rule basedApproach ； Word Accuracy Rate

參考文獻

Al-Onaizan, Y.,Knight, K.(2002).Translating named entities using monolingual and bilingual resources.Proceedings of the 40th ACL.(Proceedings of the 40th ACL).:

Arnold, D.,Balkan, L.,Humphreys, R. Lee,Meijer, S.,Sadler, L.(1995).Machine Translation: An Introductory Guide.Manchester, Oxford:NCC Blackwell.

Balkan, L.(1998).Test suites: some issues in their use and design.Proceedings of the International conference on "Machine translation: ten years on".(Proceedings of the International conference on "Machine translation: ten years on").:

Bhatia, T. K.(1993).Punjabi: a cognitive descriptive grammar.London:Routledge.

Chopde, A. (2001). Printing Transliterated Indian Language Documents, ITRANS, from website http://www.aczoom.com/itrans/idoc/idoc.html (Accessed on 22 Aug 2006).