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

Low-resource African languages have not fully benefited from the progress inneural machine translation because of a lack of data. Motivated by thischallenge we compare zero-shot learning, transfer learning and multilinguallearning on three Bantu languages (Shona, isiXhosa and isiZulu) and English.Our main target is English-to-isiZulu translation for which we have just 30,000sentence pairs, 28% of the average size of our other corpora. We show theimportance of language similarity on the performance of English-to-isiZulutransfer learning based on English-to-isiXhosa and English-to-Shona parentmodels whose BLEU scores differ by 5.2. We then demonstrate that multilinguallearning surpasses both transfer learning and zero-shot learning on ourdataset, with BLEU score improvements relative to the baselineEnglish-to-isiZulu model of 9.9, 6.1 and 2.0 respectively. Our best model alsoimproves the previous SOTA BLEU score by more than 10.

Low-Resource Neural Machine Translation for Southern African Languages