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

The NLP community has mainly focused on scaling Large Language Models (LLMs)vertically, i.e., making them better for about 100 languages. We instead scaleLLMs horizontally: we create, through continued pretraining, Glot500-m, an LLMthat covers 511 predominantly low-resource languages. An important part of thiseffort is to collect and clean Glot500-c, a corpus that covers these 511languages and allows us to train Glot500-m. We evaluate Glot500-m on fivediverse tasks across these languages. We observe large improvements for bothhigh-resource and low-resource languages compared to an XLM-R baseline. Ouranalysis shows that no single factor explains the quality of multilingual LLMrepresentations. Rather, a combination of factors determines quality includingcorpus size, script, "help" from related languages and the total capacity ofthe model. Our work addresses an important goal of NLP research: we should notlimit NLP to a small fraction of the world's languages and instead strive tosupport as many languages as possible to bring the benefits of NLP technologyto all languages and cultures. Code, data and models are available athttps://github.com/cisnlp/Glot500.

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages