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

The 2020 WMT Biomedical translation task evaluated Medline abstracttranslations. This is a small-domain translation task, meaning limited relevanttraining data with very distinct style and vocabulary. Models trained on suchdata are susceptible to exposure bias effects, particularly when trainingsentence pairs are imperfect translations of each other. This can result inpoor behaviour during inference if the model learns to neglect the sourcesentence.  The UNICAM entry addresses this problem during fine-tuning using a robustvariant on Minimum Risk Training. We contrast this approach with data-filteringto remove `problem' training examples. Under MRT fine-tuning we obtain goodresults for both directions of English-German and English-Spanish biomedicaltranslation. In particular we achieve the best English-to-Spanish translationresult and second-best Spanish-to-English result, despite using only singlemodels with no ensembling.

Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task