Generalizing Back-Translation in Neural Machine Translation
Abstract
Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabling label smoothing for the target-to-source model and (ii) sampling from a restricted search space. Our statements are investigated on the WMT 2018 German - English news translation task.
Cite
@article{arxiv.1906.07286,
title = {Generalizing Back-Translation in Neural Machine Translation},
author = {Miguel Graça and Yunsu Kim and Julian Schamper and Shahram Khadivi and Hermann Ney},
journal= {arXiv preprint arXiv:1906.07286},
year = {2019}
}
Comments
4th Conference on Machine Translation (WMT 2019) camera-ready