Dependency Reduction

method ID: dependencyreduction

Related Papers

LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization

Authors: nan

Publication: TIPSTER (2021)

DOI: nan

Fully non-autoregressive neural machine trans- lation (NAT) simultaneously predicts tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to …...

34064