4 citations · 6 across the 4 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CL2022
Parallel Attention Forcing for Machine Translation
Qingyun Dou, Mark Gales
Attention-based autoregressive models have achieved state-of-the-art performance in various sequence-to-sequence tasks, including Text-To-Speech (TTS) and Neural Machine Translatio…
cs.CL2022
Deliberation Networks and How to Train Them
Qingyun Dou, Mark Gales
Deliberation networks are a family of sequence-to-sequence models, which have achieved state-of-the-art performance in a wide range of tasks such as machine translation and speech…