From Lemmas to Links: A Lemma Bank for Ancient Greek

Colin Swaelens, Francesco Mambrini, Marco Passarotti


Abstract
This paper introduces the Greek Lemmabank, the core component of the Linking Greek knowledge base, developed according to Linked Open Data principles. Addressing the fragmentation of existing Ancient Greek resources, the lemmabank adopts a descriptive, ontology-driven approach inspired by LiLa (Linking Latin). Lemmas are modelled as canonical forms within an OntoLex-Lemon–compliant framework, preserving alternative canonical solutions and dialectal variation while enabling interoperable linking across heterogeneous datasets. The resource is populated by integrating data from the Ancient Greek WordNet and the Liddell–Scott–Jones lexicon, with additional normalisation and harmonisation to the Universal Dependencies tagset. The resulting dataset establishes a lemma-centric infrastructure for interlinking corpora, lexica, and NLP tools for Ancient Greek.
Anthology ID:
2026.lt4hala-1.10
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:
106–111
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-lt4hala-10
DOI:
10.63317/3s7ttskswwnj
Bibkey:
Cite (ACL):
Colin Swaelens, Francesco Mambrini, and Marco Passarotti. 2026. From Lemmas to Links: A Lemma Bank for Ancient Greek. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 106–111, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
From Lemmas to Links: A Lemma Bank for Ancient Greek (Swaelens et al., LT4HALA 2026)
Copy Citation: