The University of Edinburgh’s Submission to the IWSLT21 Simultaneous Translation Task
Sukanta Sen, Ulrich Germann, Barry Haddow · 2021
We describe our submission to the IWSLT 2021 shared task 1 on simultaneous text-to-text English-German translation.Our system is based on the re-translation approach where the agent re-translates the whole source prefix each time it receives a new source token.This approach has the advantage of being able to use a standard neural machine translation (NMT) inference engine with beam search, however, there is a risk that incompatibility between successive re-translations will degrade the output.To improve the quality of the translations, we experiment with various approaches: we use a fixed size wait at the beginning of the sentence, we use a language model score to detect translatable units, and we apply dynamic masking to determine when the translation is unstable.We find that a combination of dynamic masking and language model score obtains the best latency-quality trade-off.