Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
2018-04-30NAACL 2018Unverified0· sign in to hype
Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed.