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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present a novel scheme to combine neural machine translation (NMT) withtraditional statistical machine translation (SMT). Our approach borrows ideasfrom linearised lattice minimum Bayes-risk decoding for SMT. The NMT score iscombined with the Bayes-risk of the translation according the SMT lattice. Thismakes our approach much more flexible than $n$-best list or lattice rescoringas the neural decoder is not restricted to the SMT search space. We show anefficient and simple way to integrate risk estimation into the NMT decoderwhich is suitable for word-level as well as subword-unit-level NMT. We test ourmethod on English-German and Japanese-English and report significant gains overlattice rescoring on several data sets for both single and ensembled NMT. TheMBR decoder produces entirely new hypotheses far beyond simply rescoring theSMT search space or fixing UNKs in the NMT output.

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices