Search Results for author: Maximiliana Behnke

Found 5 papers, 1 papers with code

Pruning Neural Machine Translation for Speed Using Group Lasso

no code implementations WMT (EMNLP) 2021 Maximiliana Behnke, Kenneth Heafield

In the WMT 2021 Efficiency Task, our pruned and quantised models are 1. 9–2. 7x faster at the cost 0. 9–1. 7 BLEU in comparison to the unoptimised baselines.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.