Improving Zero-Shot Translation of Low-Resource Languages

Understand

Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time.

• We investigate here a zero-shot translation in a particularly lowresource multilingual setting.
• We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions.
• The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are then used together with the original parallel data to feed and iteratively re-train the multilingual network.