Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response
Computation and Language
2020-03-26 v1
Abstract
We report our experiments in building a domain-specific Tigrinya-to-English neural machine translation system. We use transfer learning from other Ge'ez script languages and report an improvement of 1.3 BLEU points over a classic neural baseline. We publish our development pipeline as an open-source library and also provide a demonstration application.
Cite
@article{arxiv.2003.11523,
title = {Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response},
author = {Alp Öktem and Mirko Plitt and Grace Tang},
journal= {arXiv preprint arXiv:2003.11523},
year = {2020}
}
Comments
Pre-print accepted to Africa NLP workshop organized within Eighth International Conference on Learning Representations (ICLR 2020)