In search of semantic distance : metaphoric and non-metaphoric constructions in static and contextual representations

Brglez, Mojca (avtor), Vintar, Špela (avtor)

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.

• Jezik: Angleški jezik
• Ključne besede: metaphor, semantic distance, word embeddings, noun phrases
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FF - Filozofska fakulteta
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Datum objave: 01.01.2025
• Leto izida: 2025
• Št. strani: Str. 207–260
• Številčenje: Vol. 13, no. 2
• PID: 20.500.12556/RUL-181926
• UDK: 81'373.72:81'322:34
• ISSN pri članku: 2299-856X
• DOI: 10.15398/jlm.v13i2.437
• COBISS.SI-ID: 254876675
• Datum objave v RUL: 20.04.2026

Gradivo je del revije

• Naslov: Journal of language modelling
• Skrajšan naslov: J. Lang. Model.
• Založnik: Institute of Computer Science, Polish Academy of Sciences
• ISSN: 2299-856X
• COBISS.SI-ID: 51953250

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: metafora, semantična razdalja, besedne vložitve, samostalniške besedne zveze

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P6-0215-2019
• Naslov: Slovenski jezik - bazične, kontrastivne in aplikativne raziskave