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

Large language models have demonstrated the capability to perform on machinetranslation when the input is prompted with a few examples (in-contextlearning). Translation quality depends on various features of the selectedexamples, such as their quality and relevance, but previous work haspredominantly focused on individual features in isolation. In this paper, wepropose a general framework for combining different features influencingexample selection. We learn a regression model, CTQ Scorer (ContextualTranslation Quality), that selects examples based on multiple features in orderto maximize the translation quality. On multiple language pairs and languagemodels, we show that CTQ Scorer helps significantly outperform random selectionas well as strong single-factor baselines reported in the literature. We alsosee an improvement of over 2.5 COMET points on average with respect to a strongBM25 retrieval-based baseline.

CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation