This paper presents the integration of CompL-it, a Linked Open Data (LOD) computational lexicon for contemporary Italian, into LiITA (Linking Italian), a Knowledge Base (KB) designed for linguistic interoperability. CompL-it contains over 101k lexical entries enriched with detailed morphological and semantic information, derived from multiple authoritative sources and modelled using the OntoLex-Lemon vocabulary. The linking process involved aligning lexical entries with lemmas in the LiITA’s Lemma Bank (LB), addressing both exact and ambiguous matches through systematic and semantically informed strategies. Moreover, 12,739 new lemmas were added to the LiITA LB. This integration enhances the expressiveness and interoperability of LiITA, enabling complex SPARQL queries that exploit the semantic network encoded in CompL-it. Examples are provided to demonstrate the advantages of querying interlinked resources.
Litta Modignani Picozzi, E. M. G., Passarotti, M. C., Moretti, G., Brasolin, P., Mambrini, F., Basile, V., Di Fabio, A., Di Palma, E., Giovannetti, E., Marchi, S., Bellandi, A., Sciolette, F., Linking CompL-it to the LiITA Knowledge Base, in Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), (Cagliari (Italia), 24-26 September 2025), CEUR Workshop Proceedings, Cagliari 2025: 595-602 [https://hdl.handle.net/10807/331457]
Linking CompL-it to the LiITA Knowledge Base
Litta Modignani Picozzi, Eleonora Maria Gabriella;Passarotti, Marco Carlo;Moretti, Giovanni;Brasolin, Paolo;Mambrini, Francesco;
2025
Abstract
This paper presents the integration of CompL-it, a Linked Open Data (LOD) computational lexicon for contemporary Italian, into LiITA (Linking Italian), a Knowledge Base (KB) designed for linguistic interoperability. CompL-it contains over 101k lexical entries enriched with detailed morphological and semantic information, derived from multiple authoritative sources and modelled using the OntoLex-Lemon vocabulary. The linking process involved aligning lexical entries with lemmas in the LiITA’s Lemma Bank (LB), addressing both exact and ambiguous matches through systematic and semantically informed strategies. Moreover, 12,739 new lemmas were added to the LiITA LB. This integration enhances the expressiveness and interoperability of LiITA, enabling complex SPARQL queries that exploit the semantic network encoded in CompL-it. Examples are provided to demonstrate the advantages of querying interlinked resources.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
