From Simultaneous to Streaming Machine Translation by Leveraging Streaming History
This work addresses the challenge of streaming machine translation for real-time applications, though it is incremental as it builds on existing sentence-level methods.
The paper tackled the problem of extending simultaneous machine translation to continuous text streams by leveraging streaming history, resulting in significant quality gains and favorable comparison to top-performing systems on IWSLT tasks.
Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously translated text. More generally, Streaming MT can be understood as an extension of Simultaneous MT to the incremental translation of a continuous input text stream. In this work, a state-of-the-art simultaneous sentence-level MT system is extended to the streaming setup by leveraging the streaming history. Extensive empirical results are reported on IWSLT Translation Tasks, showing that leveraging the streaming history leads to significant quality gains. In particular, the proposed system proves to compare favorably to the best performing systems.