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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Idioms are common in everyday language, but often pose a challenge totranslators because their meanings do not follow from the meanings of theirparts. Despite significant advances, machine translation systems still struggleto translate idiomatic expressions. We provide a simple characterization ofidiomatic translation and related issues. This allows us to conduct a syntheticexperiment revealing a tipping point at which transformer-based machinetranslation models correctly default to idiomatic translations. To expandmultilingual resources, we compile a dataset of ~4k natural sentencescontaining idiomatic expressions in French, Finnish, and Japanese. To improvetranslation of natural idioms, we introduce two straightforward yet effectivetechniques: the strategic upweighting of training loss on potentially idiomaticsentences, and using retrieval-augmented models. This not only improves theaccuracy of a strong pretrained MT model on idiomatic sentences by up to 13% inabsolute accuracy, but also holds potential benefits for non-idiomaticsentences.

Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting