%0 Conference Proceedings %T Unsupervised Neural Machine Translation for English and Manipuri %A Singh, Salam Michael %A Singh, Thoudam Doren %Y Karakanta, Alina %Y Ojha, Atul Kr. %Y Liu, Chao-Hong %Y Abbott, Jade %Y Ortega, John %Y Washington, Jonathan %Y Oco, Nathaniel %Y Lakew, Surafel Melaku %Y Pirinen, Tommi A. %Y Malykh, Valentin %Y Logacheva, Varvara %Y Zhao, Xiaobing %S Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages %D 2020 %8 December %I Association for Computational Linguistics %C Suzhou, China %F singh-singh-2020-unsupervised %X Availability of bitext dataset has been a key challenge in the conventional machine translation system which requires surplus amount of parallel data. In this work, we devise an unsupervised neural machine translation (UNMT) system consisting of a transformer based shared encoder and language specific decoders using denoising autoencoder and backtranslation with an additional Manipuri side multiple test reference. We report our work on low resource setting for English (en) - Manipuri (mni) language pair and attain a BLEU score of 3.1 for en-mni and 2.7 for mni-en respectively. Subjective evaluation on translated output gives encouraging findings. %U https://aclanthology.org/2020.loresmt-1.10 %P 69-78