학술논문
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Document Type
Working Paper
Source
Subject
Language
Abstract
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.
Comment: Proceedings of NAACL-HLT 2018
Comment: Proceedings of NAACL-HLT 2018