Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task

摘要

This paper describes the Xiaomi's submissions to the IWSLT20 shared open domain translation task for Chinese↔Japanese language pair. We explore different model ensembling strategies based on recent Transformer variants. We also further strengthen our systems via some first-line techniques, such as data filtering, data selection, tagged back translation, domain adaptation, knowledge distillation, and re-ranking. Our resulting Chinese→Japanese primary system ranked second in terms of character-level BLEU score among all submissions. Our resulting Japanese→Chinese primary system also achieved a competitive performance.