Embedded in the Labyrinth. Investigating Latin Word Senses through Transformer-Based Contextual Embeddings and Attention

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985955%3A_____%2F25%3A00642012" target="_blank" >RIV/67985955:_____/25:00642012 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Embedded in the Labyrinth. Investigating Latin Word Senses through Transformer-Based Contextual Embeddings and Attention

Original language description

This paper explores how transformer-based models can enhance historical keyword-in-context studies through automatic word sense disambiguation (WSD). Using the Latin term labyrinthus as a case study, we analyze its contextual meanings across time and genre within the GreLa corpus. A Large language model provides preliminary sense labels, which we use to evaluate 64 embedding variants—contextual, attention-based, and co-occurrence-based—derived from XLM-R and Latin BERT. Our results show that combining embedding types yields the best performance. We also illustrate how attention-based embeddings capture meaningful diachronic patterns, offering promising directions for future research on semantic change and metaphor in historical texts.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

60301 - Philosophy, History and Philosophy of science and technology

Project

<a href="/en/project/LL2320" target="_blank" >LL2320: The Origins of Modern Encyclopaedism: Launching Evolutionary Metaphorology</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů