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

Document-level neural machine translation has yielded attractiveimprovements. However, majority of existing methods roughly use all contextsentences in a fixed scope. They neglect the fact that different sourcesentences need different sizes of context. To address this problem, we proposean effective approach to select dynamic context so that the document-leveltranslation model can utilize the more useful selected context sentences toproduce better translations. Specifically, we introduce a selection module thatis independent of the translation module to score each candidate contextsentence. Then, we propose two strategies to explicitly select a variablenumber of context sentences and feed them into the translation module. We trainthe two modules end-to-end via reinforcement learning. A novel reward isproposed to encourage the selection and utilization of dynamic contextsentences. Experiments demonstrate that our approach can select adaptivecontext sentences for different source sentences, and significantly improvesthe performance of document-level translation methods.

Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning