Hybrid Approach to English-Hindi Name Entity Transliteration

TL;DR

This paper presents a hybrid rule-based and statistical method for English-Hindi name entity transliteration, achieving 83.40% accuracy in converting English names to Hindi.

Contribution

It introduces a novel hybrid approach combining rule-based phoneme extraction with statistical translation for improved transliteration accuracy.

Findings

Achieved 83.40% transliteration accuracy

Demonstrated effectiveness of hybrid approach in Indian language MT

Improved transliteration over existing methods

Abstract

Machine translation (MT) research in Indian languages is still in its infancy. Not much work has been done in proper transliteration of name entities in this domain. In this paper we address this issue. We have used English-Hindi language pair for our experiments and have used a hybrid approach. At first we have processed English words using a rule based approach which extracts individual phonemes from the words and then we have applied statistical approach which converts the English into its equivalent Hindi phoneme and in turn the corresponding Hindi word. Through this approach we have attained 83.40% accuracy.