Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation
This work addresses robustness in neural machine translation for noisy text, but it is incremental as it builds on existing data augmentation and back-translation approaches.
The paper tackled the problem of neural machine translation models being sensitive to input noise by proposing new data augmentation methods to extend limited noisy data, improving robustness while keeping models small, and exploring the use of external noise from speech transcripts to enhance performance.
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to extend limited noisy data and further improve NMT robustness to noise while keeping the models small. Secondly, we explore the effect of utilizing noise from external data in the form of speech transcripts and show that it could help robustness.