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

In neural machine translation (NMT), the most common practice is to stack anumber of recurrent or feed-forward layers in the encoder and the decoder. As aresult, the addition of each new layer improves the translation qualitysignificantly. However, this also leads to a significant increase in the numberof parameters. In this paper, we propose to share parameters across all thelayers thereby leading to a recurrently stacked NMT model. We empirically showthat the translation quality of a model that recurrently stacks a single layer6 times is comparable to the translation quality of a model that stacks 6separate layers. We also show that using pseudo-parallel corpora byback-translation leads to further significant improvements in translationquality.

Recurrent Stacking of Layers for Compact Neural Machine Translation Models