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

Lexical ambiguity is a challenging and pervasive problem in machinetranslation (\mt). We introduce a simple and scalable approach to resolvetranslation ambiguity by incorporating a small amount of extra-sententialcontext in neural \mt. Our approach requires no sense annotation and no changeto standard model architectures. Since actual document context is not availablefor the vast majority of \mt training data, we collect related sentences foreach input to construct pseudo-documents. Salient words from pseudo-documentsare then encoded as a prefix to each source sentence to condition thegeneration of the translation. To evaluate, we release \docmucow, a challengeset for translation disambiguation based on the English-German \mucow\cite{raganato-etal-2020-evaluation} augmented with document IDs. Extensiveexperiments show that our method translates ambiguous source words better thanstrong sentence-level baselines and comparable document-level baselines whilereducing training costs.

Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context