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

Neural machine translation (NMT) has progressed rapidly over the past severalyears, and modern models are able to achieve relatively high quality using onlymonolingual text data, an approach dubbed Unsupervised Machine Translation(UNMT). However, these models still struggle in a variety of ways, includingaspects of translation that for a human are the easiest - for instance,correctly translating common nouns. This work explores a cheap and abundantresource to combat this problem: bilingual lexica. We test the efficacy ofbilingual lexica in a real-world set-up, on 200-language translation modelstrained on web-crawled text. We present several findings: (1) using lexicaldata augmentation, we demonstrate sizable performance gains for unsupervisedtranslation; (2) we compare several families of data augmentation,demonstrating that they yield similar improvements, and can be combined foreven greater improvements; (3) we demonstrate the importance of carefullycurated lexica over larger, noisier ones, especially with larger models; and(4) we compare the efficacy of multilingual lexicon data versushuman-translated parallel data. Finally, we open-source GATITOS (available athttps://github.com/google-research/url-nlp/tree/main/gatitos), a newmultilingual lexicon for 26 low-resource languages, which had the highestperformance among lexica in our experiments.

Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation