Octanove Labs' Japanese-Chinese Open Domain Translation System
This paper describes Octanove Labs{'} submission to the IWSLT 2020 open domain translation challenge. In order to build a high-quality Japanese-Chinese neural machine translation (NMT) system, we use a combination of 1) parallel corpus filtering and 2) back-translation. We have shown that, by using heuristic rules and learned classifiers, the size of the parallel data can be reduced by 70{\%} to 90{\%} without much impact on the final MT performance. We have also shown that including the artificially generated parallel data through back-translation further boosts the metric by 17{\%} to 27{\%}, while self-training contributes little. Aside from a small number of parallel sentences annotated for filtering, no external resources have been used to build our system.
PDF Abstract