@inproceedings{7b564cee16bb4aaf8a05283706b04fc8,
title = "Introducing EM-FT for Manipuri-English Neural Machine Translation",
abstract = "This paper introduces pretrained word embeddings for Manipuri, a low-resourced Indian language. The pretrained word embeddings based on fastText is capable of handling the highly agglutinative language Manipuri (mni). We then perform machine translation (MT) experiments using neural network (NN) models. In this paper, we confirm the following observations. Firstly, the reported BLEU score of the Transformer architecture with fastText word embedding model EM-FT performs better than without in all the NMT experiments. Secondly, we observe that adding more training data from a different domain of the test data negatively impacts translation accuracy. The resources reported in this paper are made available in the ELRA catalogue to help the low-resourced languages community with MT/NLP tasks.",
keywords = "language technology, low resource language, neural machine translation",
author = "Rudali Huidrom and Yves Lepage",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; 6th Workshop on Indian Language Data: Resources and Evaluation, WILDRE 2022 ; Conference date: 20-06-2022",
year = "2022",
language = "English",
series = "6th Workshop on Indian Language Data: Resources and Evaluation, WILDRE 2022 - held in conjunction with the International Conference on Language Resources and Evaluation, LREC 2022 - Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "1--6",
editor = "Jha, {Girish Nath} and Devi, {Sobha Lalitha} and Kalika Bali and Ojha, {Atul Kr.}",
booktitle = "6th Workshop on Indian Language Data",
}