Improving Robustness of Machine Translation with Synthetic Noise
This work addresses the issue of translation accuracy degradation for users dealing with noisy text, but it is incremental as it builds on existing datasets and methods.
The paper tackled the problem of machine translation systems performing poorly on noisy human-generated text, such as social media, by using the MTNT dataset to synthesize noise in clean data, resulting in improved robustness and partially mitigating accuracy loss.
Modern Machine Translation (MT) systems perform consistently well on clean, in-domain text. However most human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can have a disastrous impact on the accuracy of output translation. In this paper we leverage the Machine Translation of Noisy Text (MTNT) dataset to enhance the robustness of MT systems by emulating naturally occurring noise in otherwise clean data. Synthesizing noise in this manner we are ultimately able to make a vanilla MT system resilient to naturally occurring noise and partially mitigate loss in accuracy resulting therefrom.