2026-06-06T02:36:37Zhttps://iris.cnr.it/oai/request

oai:iris.cnr.it:20.500.14243/5712232026-03-05T01:37:05Zou_ou239

Low- vs High-level Lemmatization for Historical Languages. A Case study on Italian Chiara Alzetta Simonetta Montemagni Alzetta, Chiara Montemagni, Simonetta Data-driven Lemmatization, Historical Italian, Universal Dependencies, Normalization Lemmatization remains a foundational yet challenging task in the processing of historical Italian texts, due to the complex interplay of orthographic, morphological, and diatopic variation. A crucial, yet often overlooked, aspect is the degree of normalization applied during lemmatization. A conservative approach preserves attested historical forms, ensuring greater linguistic fidelity but increasing data sparsity. Conversely, an abstract normalization strategy aligns historical variants with standardized contemporary lemmas, improving generalization but potentially introducing inaccurate mappings. In this paper, we present a comparative evaluation of conservative and normalized lemmatization strategies for historical Italian. To our knowledge, this is the first study to explicitly assess the impact of lemmatization strategies in the context of historical languages, particularly those that are morphologically rich. Our results indicate that high-level normalization offers a promising trade-off between precision and generalization. 2025 info:eu-repo/semantics/conferenceObject https://hdl.handle.net/20.500.14243/571223 info:eu-repo/semantics/altIdentifier/isbn/979-12-243-0587-3 https://aclanthology.org/2025.clicit-1.4.pdf eng ispartofbook:Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025) Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025) numberofpages:10 ELETTRONICO CEUR Workshop Proceeding