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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We propose a novel language-independent approach for improving machinetranslation for resource-poor languages by exploiting their similarity toresource-rich ones. More precisely, we improve the translation from aresource-poor source language X_1 into a resource-rich language Y given abi-text containing a limited number of parallel sentences for X_1-Y and alarger bi-text for X_2-Y for some resource-rich language X_2 that is closelyrelated to X_1. This is achieved by taking advantage of the opportunities thatvocabulary overlap and similarities between the languages X_1 and X_2 inspelling, word order, and syntax offer: (1) we improve the word alignments forthe resource-poor language, (2) we further augment it with additionaltranslation options, and (3) we take care of potential spelling differencesthrough appropriate transliteration. The evaluation for Indonesian- >Englishusing Malay and for Spanish -> English using Portuguese and pretending Spanishis resource-poor shows an absolute gain of up to 1.35 and 3.37 BLEU points,respectively, which is an improvement over the best rivaling approaches, whileusing much less additional data. Overall, our method cuts the amount ofnecessary "real training data by a factor of 2--5.

Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages