Fast Interleaved Bidirectional Sequence Generation
WMT@EMNLP, pp. 503-515, 2020.
Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring tokens (semi-autoregressive decoding, SA), we take inspiration from bidirectional sequence generation and introduce a decod...More
PPT (Upload PPT)