<?xml version="1.0"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/"><rdf:Description rdf:about="https://repozitorij.uni-lj.si/IzpisGradiva.php?id=181926"><dc:title>In search of semantic distance</dc:title><dc:creator>Brglez,	Mojca	(Avtor)
	</dc:creator><dc:creator>Vintar,	Špela	(Avtor)
	</dc:creator><dc:subject>metaphor</dc:subject><dc:subject>semantic distance</dc:subject><dc:subject>word embeddings</dc:subject><dc:subject>noun phrases</dc:subject><dc:description>Phrases such as burning question, digital waste or invasion of technol- ogy are relatively ordinary expressions understood by any speaker of English. While diverse in structure and meaning, they demonstrate a semantic tension between the basic meanings of a metaphoric and a non-metaphoric constituent. Albeit frequent in discourse, they remain a challenge for automatic language processing systems, especially for smaller, less represented languages. In this work, we inspect a broad array of language models to embed noun phrases in Slovene and in- vestigate the potential of word embeddings to identify metaphoric phrases via the semantic distance of its constituents as measured via cosine similarity. The study shows both static and contextual mono- lingual embeddings encode relevant semantic information while mul- tilingual embeddings demonstrate no significant effect in this exper- imental setting. Moreover, the study unravels the most effective lay- ers for basic meaning representation and highlights the influence of other, non-semantic factors on cosine similarity. By shedding light on these mechanisms, the study provides new insights for both metaphor processing and our understanding of the inner workings of language models.</dc:description><dc:date>2025</dc:date><dc:date>2026-04-20 10:35:30</dc:date><dc:type>Članek v reviji</dc:type><dc:identifier>181926</dc:identifier><dc:language>sl</dc:language></rdf:Description></rdf:RDF>
