Improving Robustness in Real-World Neural Machine Translation Engines
This work tackles robustness problems for commercial machine translation providers, but appears incremental as it focuses on existing methods applied to real-world data without introducing new paradigms.
The paper addresses robustness challenges in practical neural machine translation engines, describing specific issues and approaches to improve them in real-world scenarios, but does not provide concrete numerical results.
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.