From The Digital Classicist Wiki
Jump to navigation Jump to search



To cite all versions of LEMLAT 3.0, you can adapt the following:

Marco Passarotti, Paolo Ruffolo, Flavio M. Cecchini, Eleonora Litta, Marco Budassi (2018) LEMLAT 3.0. DOI: https://doi.org/10.5281/zenodo.1492133

DOIs for the individual releases of LEMLAT 3.0 are available under DOI: https://doi.org/10.5281/zenodo.1492133


LemLat is a morphological analyser and lemmatiser for Latin.

Developed in the early 1990s by Andrea Bozzi, Giuseppe Cappelli and Nino Marinone to lemmatise the Grammatici Latini texts, it was improved in 2002-2004 with the addition of morphological traits within the European project CHLT ('Cultural Heritage Language Technologies') by Marco Passarotti, Paolo Ruffolo and Andrea Bozzi at the ILC-CNR in Pisa. The lexical basis of the first version of LEMLAT is the result of the collation of three Latin dictionaries (Georges and Georges, 1913-1918; Glare, 1982; Gradenwitz, 1904). It counted 40,014 lexical entries and 43,432 lemmas.

A further upgrade to the lexical base of LEMLAT, known as LEMLAT3, was developed by the CIRCSE Research Centre at the Università Cattolica del Sacro Cuore in Milan; LEMLAT3 includes 26,250 lemmas from Forcellini's Onomasticon (1940) and 82,556 from Du Cange's Glossarium Mediae et Infimae Latinitatis (1883-1887). A Marie Curie (MSCA Individual Fellowship) funded project, Word Formation Latin, is currently working on establishing word formation relations between the lexical entries of LEMLAT’s BASE (Georges and Georges, 1913-1918; Glare, 1982; Gradenwitz, 1904) lexicon.


  • Bozzi, A., & Cappelli, G.. (1990). A Project for Latin Lexicography: 2. A Latin Morphological Analyzer. Computers and the Humanities, 24(5/6), 421–426. Retrieved from http://www.jstor.org/stable/30204177
  • Cappelli Giuseppe, Passarotti Marco, LemLat: uno strumento computazionale per l’analisi linguistica del latino. Sviluppo e prospettive, «Euphrosyne», XXXI, 2003, pp. 519-531.
  • Lomanto Valeria ; Marinone Nino, Philologie et informatique : résultats et projets. RISSH 1994 30 : 55-74 [rés. en angl.] [report on four computerized works about Latin language : a concordance to Symmachus (cf. APh LIV Nᵒ 4776), a concordance based on Keil's collection of the Latin grammarians (Leipzig 1855-1890), an index to Latin grammar texts (cf. APh LXI Nᵒ 1601), a project for automatic lemmatization of Latin. The various problems are discussed and the accepted solutions are described]
  • Marinone, N.. (1990). A Project for Latin Lexicography: 1. Automatic Lemmatization and Word-List. Computers and the Humanities, 24(5/6), 417–420. Retrieved from http://www.jstor.org/stable/30204176
  • Marinone Nino, Lessico latino e analisi elettronica. Voces 1990 I : 23-28 rés. en angl. p. 121 [rés. en eng]. [grandes lignes d'un projet en cours de réalisation visant à la constitution d'un vaste répertoire lexical informatisé]
  • Passarotti Marco, Ruffolo Paolo, L’utilizzo del lemmatizzatore LEMLAT per una sistematizzazione dell’omografia in latino, «Euphrosyne», XXXII, 2004, pp. 99-110.
  • Passarotti Marco, Development and perspectives of the Latin morphological analyser LEMLAT, in Bozzi Andrea, Cignoni Laura, Lebrave Jean-Louis (a cura di), Digital Technology and Philological Disciplines, «Linguistica Computazionale», XX-XXI, 2004, pp. 397-414.
  • Passarotti Marco, LEMLAT. Uno strumento per la lemmatizzazione morfologica automatica del latino, in Citti Francesco, Del Vecchio Tommaso (a cura di), From Manuscript to Digital Text. Problems of Interpretation and Markup. Proceedings of the Colloquium (Bologna, June 12th 2003), «Papers on Grammar», IX-3, Roma, Herder, 2007, pp. 107-128.