Iterative Batch Back-Translation for Neural Machine Translation: A Conceptual Model
Abstract
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation has been shown to outperform standard back-translation albeit on some language pairs. This work proposes the iterative batch back-translation that is aimed at enhancing the standard iterative back-translation and enabling the efficient utilization of more monolingual data. After each iteration, improved back-translations of new sentences are added to the parallel data that will be used to train the final forward model. The work presents a conceptual model of the proposed approach.
Cite
@article{arxiv.2001.11327,
title = {Iterative Batch Back-Translation for Neural Machine Translation: A Conceptual Model},
author = {Idris Abdulmumin and Bashir Shehu Galadanci and Abubakar Isa},
journal= {arXiv preprint arXiv:2001.11327},
year = {2020}
}
Comments
This article was a proposal, a conceptual model and, thereby, substantially overlapping with arXiv:1912.10514. This research has been substantially reworked. Some of the findings are presented in arXiv:1912.10514, arXiv:2006.02876 and arXiv:2011.07403. The final work will be submitted for publishing in due course