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 number of senses of a given word, or polysemy, is a very subjectivenotion, which varies widely across annotators and resources. We propose a novelmethod to estimate polysemy, based on simple geometry in the contextualembedding space. Our approach is fully unsupervised and purely data-driven. Weshow through rigorous experiments that our rankings are well correlated (withstrong statistical significance) with 6 different rankings derived from famoushuman-constructed resources such as WordNet, OntoNotes, Oxford, Wikipedia etc.,for 6 different standard metrics. We also visualize and analyze the correlationbetween the human rankings. A valuable by-product of our method is the abilityto sample, at no extra cost, sentences containing different senses of a givenword. Finally, the fully unsupervised nature of our method makes it applicableto any language.  Code and data are publicly available athttps://github.com/ksipos/polysemy-assessment .  The paper was accepted as a long paper at EACL 2021.

Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings