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

Non-autoregressive translation (NAT) model achieves a much faster inferencespeed than the autoregressive translation (AT) model because it cansimultaneously predict all tokens during inference. However, its translationquality suffers from degradation compared to AT. And existing NAT methods onlyfocus on improving the NAT model's performance but do not fully utilize it. Inthis paper, we propose a simple but effective method called "Candidate Soups,"which can obtain high-quality translations while maintaining the inferencespeed of NAT models. Unlike previous approaches that pick the individual resultand discard the remainders, Candidate Soups (CDS) can fully use the valuableinformation in the different candidate translations through model uncertainty.Extensive experiments on two benchmarks (WMT'14 EN-DE and WMT'16 EN-RO)demonstrate the effectiveness and generality of our proposed method, which cansignificantly improve the translation quality of various base models. Morenotably, our best variant outperforms the AT model on three translation taskswith 7.6 times speedup.

Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation