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

Human languages are full of metaphorical expressions. Metaphors help peopleunderstand the world by connecting new concepts and domains to more familiarones. Large pre-trained language models (PLMs) are therefore assumed to encodemetaphorical knowledge useful for NLP systems. In this paper, we investigatethis hypothesis for PLMs, by probing metaphoricity information in theirencodings, and by measuring the cross-lingual and cross-dataset generalizationof this information. We present studies in multiple metaphor detection datasetsand in four languages (i.e., English, Spanish, Russian, and Farsi). Ourextensive experiments suggest that contextual representations in PLMs do encodemetaphorical knowledge, and mostly in their middle layers. The knowledge istransferable between languages and datasets, especially when the annotation isconsistent across training and testing sets. Our findings give helpful insightsfor both cognitive and NLP scientists.

Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages