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

Neural machine translation (NMT) has arguably achieved human level paritywhen trained and evaluated at the sentence-level. Document-level neural machinetranslation has received less attention and lags behind its sentence-levelcounterpart. The majority of the proposed document-level approaches investigateways of conditioning the model on several source or target sentences to capturedocument context. These approaches require training a specialized NMT modelfrom scratch on parallel document-level corpora. We propose an approach thatdoesn't require training a specialized model on parallel document-level corporaand is applied to a trained sentence-level NMT model at decoding time. Weprocess the document from left to right multiple times and self-train thesentence-level model on pairs of source sentences and generated translations.Our approach reinforces the choices made by the model, thus making it morelikely that the same choices will be made in other sentences in the document.We evaluate our approach on three document-level datasets: NISTChinese-English, WMT'19 Chinese-English and OpenSubtitles English-Russian. Wedemonstrate that our approach has higher BLEU score and higher human preferencethan the baseline. Qualitative analysis of our approach shows that choices madeby model are consistent across the document.

Capturing document context inside sentence-level neural machine translation models with self-training