Picture for William Tambellini

William Tambellini

Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

Add code
Apr 30, 2018
Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne
Figure 1 for Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Figure 2 for Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Figure 3 for Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Figure 4 for Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

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.

* Proceedings of NAACL-HLT 2018 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon