Evaluating Hierarchical Aggregation and LLM-Based Matching for Synset Selection in Ancient Greek

Luca Brigada Villa, Marco Passarotti, Chiara Zanchi, Riccardo Ginevra, Erica Fratellini, Eleonora Litta


Abstract
This paper presents a structured framework for WordNet synset selection applied to Ancient Greek lexical material. Starting from synonym definitions extracted from the Liddell–Scott–Jones (LSJ) lexicon, we compare two strategies: hierarchy-driven aggregation via bounded hypernym trees and LLM-based definitional matching with pairwise ranking. Graded human evaluation shows that structure-aware methods provide a robust baseline, particularly for nouns and verbs, while LLM-based reranking does not consistently improve performance, especially for highly ploysemous groups of synonyms. Beyond supporting the development of an Ancient Greek WordNet, the study highlights the methodological portability of the framework to other languages and lexical resources.
Anthology ID:
2026.lt4hala-1.38
Volume:
Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Rachele Sprugnoli, Marco Passarotti
Venues:
LT4HALA | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
368–379
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-lt4hala-38
DOI:
10.63317/29d5dhmeqrn6
Bibkey:
Cite (ACL):
Luca Brigada Villa, Marco Passarotti, Chiara Zanchi, Riccardo Ginevra, Erica Fratellini, and Eleonora Litta. 2026. Evaluating Hierarchical Aggregation and LLM-Based Matching for Synset Selection in Ancient Greek. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 368–379, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Evaluating Hierarchical Aggregation and LLM-Based Matching for Synset Selection in Ancient Greek (Brigada Villa et al., LT4HALA 2026)
Copy Citation: