In this work, we focus on the development of machine translation (MT) models of a lowresource language pair viz. English-Manipuri. Manipuri is one of the eight scheduled languages of the Indian constitution. Manipuri is currently written in two different scripts: one is its original script called Meitei Mayek and the other is the Bengali script. We evaluate the performance of English-Manipuri MT models based on transformer and transfer learning technique. Our MT models are trained using a dataset of 69,065 parallel sentences and validated on 500 sentences. Using 500 test sentences, the English to Manipuri MT models achieved a BLEU score of 19.13 and 29.05 with mT5 and OpenNMT respectively. The results demonstrate that the OpenNMT model significantly outperforms the mT5 model. Additionally, Manipuri to English MT system trained with OpenNMT model reported a BLEU score of 30.90. We also carried out a comparative analysis between the Bengali script and the transliterated Meitei Mayek script for English-Manipuri MT models. This analysis reveals that the transliterated version enhances the MT model performance resulting in a notable +2.35 improvement in the BLEU score.

This paper describes the transformer-based Neural Machine translation (NMT) system for the Low-Resource Indic Language Translation task for the English-Manipuri language pair submitted by the Centre for Natural Language Processing in National Institute of Technology Silchar, India (NITS-CNLP) in the WMT 2023 shared task. The model attained an overall BLEU score of 22.75 and 26.92 for the English to Manipuri and Manipuri to English translations respectively. Experimental results for English to Manipuri and Manipuri to English models for character level n-gram F-score (chrF) of 48.35 and 48.64, RIBES of 0.61 and 0.65, TER of 70.02 and 67.62, as well as COMET of 0.70 and 0.66 respectively are reported.