Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report
This work addresses the problem of robust machine translation for social media, where noise and domain differences pose difficulties, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackled the challenge of translating social media text, which differs from normal corpora and has limited parallel data, by using a domain sensitive training method and generating pseudo noisy sources from monolingual data, achieving over 10 BLEU improvement in both En-Fr and Fr-En translations compared to baselines.
This paper describes the machine translation system developed jointly by Baidu Research and Oregon State University for WMT 2019 Machine Translation Robustness Shared Task. Translation of social media is a very challenging problem, since its style is very different from normal parallel corpora (e.g. News) and also include various types of noises. To make it worse, the amount of social media parallel corpora is extremely limited. In this paper, we use a domain sensitive training method which leverages a large amount of parallel data from popular domains together with a little amount of parallel data from social media. Furthermore, we generate a parallel dataset with pseudo noisy source sentences which are back-translated from monolingual data using a model trained by a similar domain sensitive way. We achieve more than 10 BLEU improvement in both En-Fr and Fr-En translation compared with the baseline methods.