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

This work studies the semantic representations learned by BERT for compounds,that is, expressions such as sunlight or bodyguard. We build on recent studiesthat explore semantic information in Transformers at the word level and testwhether BERT aligns with human semantic intuitions when dealing withexpressions (e.g., sunlight) whose overall meaning depends -- to a variousextent -- on the semantics of the constituent words (sun, light). We leverage adataset that includes human judgments on two psycholinguistic measures ofcompound semantic analysis: lexeme meaning dominance (LMD; quantifying theweight of each constituent toward the compound meaning) and semantictransparency (ST; evaluating the extent to which the compound meaning isrecoverable from the constituents' semantics). We show that BERT-based measuresmoderately align with human intuitions, especially when using contextualizedrepresentations, and that LMD is overall more predictable than ST. Contrary tothe results reported for 'standard' words, higher, more contextualized layersare the best at representing compound meaning. These findings shed new light onthe abilities of BERT in dealing with fine-grained semantic phenomena.Moreover, they can provide insights into how speakers represent compounds.

A Psycholinguistic Analysis of BERT's Representations of Compounds