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

Concepts play a central role in many applications. This includes settingswhere concepts have to be modelled in the absence of sentence context. Previouswork has therefore focused on distilling decontextualised concept embeddingsfrom language models. But concepts can be modelled from different perspectives,whereas concept embeddings typically mostly capture taxonomic structure. Toaddress this issue, we propose a strategy for identifying what differentconcepts, from a potentially large concept vocabulary, have in common withothers. We then represent concepts in terms of the properties they share withthe other concepts. To demonstrate the practical usefulness of this way ofmodelling concepts, we consider the task of ultra-fine entity typing, which isa challenging multi-label classification problem. We show that by augmentingthe label set with shared properties, we can improve the performance of thestate-of-the-art models for this task.

What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabularies