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

Analysing translation quality in regards to specific linguistic phenomena hashistorically been difficult and time-consuming. Neural machine translation hasthe attractive property that it can produce scores for arbitrary translations,and we propose a novel method to assess how well NMT systems model specificlinguistic phenomena such as agreement over long distances, the production ofnovel words, and the faithful translation of polarity. The core idea is that wemeasure whether a reference translation is more probable under a NMT model thana contrastive translation which introduces a specific type of error. We presentLingEval97, a large-scale data set of 97000 contrastive translation pairs basedon the WMT English->German translation task, with errors automatically createdwith simple rules. We report results for a number of systems, and find thatrecently introduced character-level NMT systems perform better attransliteration than models with byte-pair encoding (BPE) segmentation, butperform more poorly at morphosyntactic agreement, and translating discontiguousunits of meaning.

How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs