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

Language Models are the core for almost any Natural Language Processingsystem nowadays. One of their particularities is their contextualizedrepresentations, a game changer feature when a disambiguation between wordsenses is necessary. In this paper we aim to explore to what extent languagemodels are capable of discerning among senses at inference time. We performedthis analysis by prompting commonly used Languages Models such as BERT orRoBERTa to perform the task of Word Sense Disambiguation (WSD). We leverage therelation between word senses and domains, and cast WSD as a textual entailmentproblem, where the different hypothesis refer to the domains of the wordsenses. Our results show that this approach is indeed effective, close tosupervised systems.

What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories