Can neural machine translation do simultaneous translation?
This work addresses the challenge of real-time translation for applications like live interpretation, though it is a first step and incremental in building a full system.
The authors tackled the problem of enabling neural machine translation to perform simultaneous translation by introducing a novel decoding algorithm that allows translation to begin before the full source sentence is received, resulting in a method that jointly handles segmentation and translation to improve quality.
We investigate the potential of attention-based neural machine translation in simultaneous translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding, that allows an existing neural machine translation model to begin translating before a full source sentence is received. This approach is unique from previous works on simultaneous translation in that segmentation and translation are done jointly to maximize the translation quality and that translating each segment is strongly conditioned on all the previous segments. This paper presents a first step toward building a full simultaneous translation system based on neural machine translation.