Attention based Sequence to Sequence Learning for Machine Translation of Low Resourced Indic Languages -- A case of Sanskrit to Hindi

TL;DR

This paper introduces an attention-based neural machine translation model for Sanskrit to Hindi, demonstrating high accuracy and BLEU scores despite the low-resource nature of Sanskrit, by constructing a parallel corpus and focusing on long-term dependencies.

Contribution

It presents a novel Sanskrit-Hindi parallel corpus and applies an attention mechanism in NMT to improve translation quality for low-resource Indic languages.

Findings

Achieved 88% accuracy in human evaluation

Attained a BLEU score of 0.92

Demonstrated effective alignment with attention plots

Abstract

Deep Learning techniques are powerful in mimicking humans in a particular set of problems. They have achieved a remarkable performance in complex learning tasks. Deep learning inspired Neural Machine Translation (NMT) is a proficient technique that outperforms traditional machine translation. Performing machine-aided translation on Indic languages has always been a challenging task considering their rich and diverse grammar. The neural machine translation has shown quality results compared to the traditional machine translation approaches. The fully automatic machine translation becomes problematic when it comes to low-resourced languages, especially with Sanskrit. This paper presents attention mechanism based neural machine translation by selectively focusing on a particular part of language sentences during translation. The work shows the construction of Sanskrit to Hindi bilingual parallel corpus with nearly 10K samples and having 178,000 tokens. The neural translation model equipped with an attention mechanism has been trained on Sanskrit to Hindi parallel corpus. The approach has shown the significance of attention mechanisms to overcome long-term dependencies, primarily associated with low resources Indic languages. The paper shows the attention plots on testing data to demonstrate the alignment between source and translated words. For the evaluation of the translated sentences, manual score based human evaluation and automatic evaluation metric based techniques have been adopted. The attention mechanism based neural translation has achieved 88% accuracy in human evaluation and a BLEU score of 0.92 on Sanskrit to Hindi translation.