Iterative Batch Back-Translation for Neural Machine Translation: A Conceptual Model
This is an incremental improvement for neural machine translation researchers and practitioners, focusing on data augmentation methods.
The paper tackles the problem of generating parallel sentences for neural machine translation by proposing iterative batch back-translation, which enhances standard iterative back-translation to more efficiently utilize monolingual data, though no concrete results or numbers are provided.
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.