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

With the methodological support of probing (or diagnostic classification),recent studies have demonstrated that Transformers encode syntactic andsemantic information to some extent. Following this line of research, thispaper aims at taking semantic probing to an abstraction extreme with the goalof answering the following research question: can contemporaryTransformer-based models reflect an underlying Foundational Ontology? To thisend, we present a systematic Foundational Ontology (FO) probing methodology toinvestigate whether Transformers-based models encode abstract semanticinformation. Following different pre-training and fine-tuning regimes, wepresent an extensive evaluation of a diverse set of large-scale language modelsover three distinct and complementary FO tagging experiments. Specifically, wepresent and discuss the following conclusions: (1) The probing results indicatethat Transformer-based models incidentally encode information related toFoundational Ontologies during the pre-training pro-cess; (2) Robust FO taggers(accuracy of 90 percent)can be efficiently built leveraging on this knowledge.

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language