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

Pre-trained language models (LMs) encode rich information about linguisticstructure but their knowledge about lexical polysemy remains unclear. Wepropose a novel experimental setup for analysing this knowledge in LMsspecifically trained for different languages (English, French, Spanish andGreek) and in multilingual BERT. We perform our analysis on datasets carefullydesigned to reflect different sense distributions, and control for parametersthat are highly correlated with polysemy such as frequency and grammaticalcategory. We demonstrate that BERT-derived representations reflect words'polysemy level and their partitionability into senses. Polysemy-relatedinformation is more clearly present in English BERT embeddings, but models inother languages also manage to establish relevant distinctions between words atdifferent polysemy levels. Our results contribute to a better understanding ofthe knowledge encoded in contextualised representations and open up new avenuesfor multilingual lexical semantics research.

Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses