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

We explore the possibility of meta-learning for the language-independentunsupervised tokenization problem for English, Russian, and Chinese. Weimplement the meta-learning approach for automatic determination ofhyper-parameters of the unsupervised tokenization model proposed in earlierworks, relying on various human-independent fitness functions such asnormalised anti-entropy, compression factor and cross-split F1 score, as wellas additive and multiplicative composite combinations of the three metrics,testing them against the conventional F1 tokenization score. We find a fairlygood correlation between the latter and the additive combination of the formerthree metrics for English and Russian. In case of Chinese, we find asignificant correlation between the F 1 score and the compression factor. Ourresults suggest the possibility of robust unsupervised tokenization oflow-resource and dead languages and allow us to think about human languages interms of the evolution of efficient symbolic communication codes with differentstructural optimisation schemes that have evolved in different human cultures.

Self-tuning hyper-parameters for unsupervised cross-lingual tokenization