English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although neural machine translation has achieved promising results, itsuffers from slow translation speed. The direct consequence is that a trade-offhas to be made between translation quality and speed, thus its performance cannot come into full play. We apply cube pruning, a popular technique to speed updynamic programming, into neural machine translation to speed up thetranslation. To construct the equivalence class, similar target hidden statesare combined, leading to less RNN expansion operations on the target side andless \$\mathrm{softmax}\$ operations over the large target vocabulary. Theexperiments show that, at the same or even better translation quality, ourmethod can translate faster compared with naive beam search by \$3.3\times\$ onGPUs and \$3.5\times\$ on CPUs.

Speeding Up Neural Machine Translation Decoding by Cube Pruning