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

Although neural-based machine translation evaluation metrics, such as COMETor BLEURT, have achieved strong correlations with human judgements, they aresometimes unreliable in detecting certain phenomena that can be considered ascritical errors, such as deviations in entities and numbers. In contrast,traditional evaluation metrics, such as BLEU or chrF, which measure lexical orcharacter overlap between translation hypotheses and human references, havelower correlations with human judgements but are sensitive to such deviations.In this paper, we investigate several ways of combining the two approaches inorder to increase robustness of state-of-the-art evaluation methods totranslations with critical errors. We show that by using additional informationduring training, such as sentence-level features and word-level tags, thetrained metrics improve their capability to penalize translations with specifictroublesome phenomena, which leads to gains in correlation with human judgmentsand on recent challenge sets on several language pairs.

BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation