Towards Sense to Sense Linking across DBnary Languages

Gilles Sérasset


Abstract
39 Since 2012, the DBnary project extracts lexical information from different Wiktionary language editions (26 editions in 2025) and makes it available to the community as queryable RDF data (modeled using ontolex-lemon ontology). This dataset contains more than 12M translations linking languages at the level of Lexical Entries. This paper presents an effort to automatically link the DBnary languages at the Lexical Sense level. For this we explore different ways to compute cross-lingual semantic similarity, using multilingual language models.
Anthology ID:
2025.ldk-1.32
Volume:
Proceedings of the 5th Conference on Language, Data and Knowledge
Month:
September
Year:
2025
Address:
Naples, Italy
Editors:
Mehwish Alam, Andon Tchechmedjiev, Jorge Gracia, Dagmar Gromann, Maria Pia di Buono, Johanna Monti, Maxim Ionov
Venues:
LDK | WS
SIG:
Publisher:
Unior Press
Note:
Pages:
318–327
Language:
URL:
https://preview.aclanthology.org/ldl-25-ingestion/2025.ldk-1.32/
DOI:
Bibkey:
Cite (ACL):
Gilles Sérasset. 2025. Towards Sense to Sense Linking across DBnary Languages. In Proceedings of the 5th Conference on Language, Data and Knowledge, pages 318–327, Naples, Italy. Unior Press.
Cite (Informal):
Towards Sense to Sense Linking across DBnary Languages (Sérasset, LDK 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ldl-25-ingestion/2025.ldk-1.32.pdf