Improving Robustness in Real-World Neural Machine Translation Engines
Computation and Language
2019-07-03 v1
Abstract
As a commercial provider of machine translation, we are constantly training engines for a variety of uses, languages, and content types. In each case, there can be many variables, such as the amount of training data available, and the quality requirements of the end user. These variables can have an impact on the robustness of Neural MT engines. On the whole, Neural MT cures many ills of other MT paradigms, but at the same time, it has introduced a new set of challenges to address. In this paper, we describe some of the specific issues with practical NMT and the approaches we take to improve model robustness in real-world scenarios.
Cite
@article{arxiv.1907.01279,
title = {Improving Robustness in Real-World Neural Machine Translation Engines},
author = {Rohit Gupta and Patrik Lambert and Raj Nath Patel and John Tinsley},
journal= {arXiv preprint arXiv:1907.01279},
year = {2019}
}
Comments
6 Pages, Accepted in Machine Translation Summit 2019