What’s Going On in Milan? A Practical Introduction to Resources and Tools for Latin at the CIRCSE Research Centre

The talk provides an overview of the activities ongoing at the CIRCSE research centre of Univeristà Cattolica del Sacro Cuore (Milan, Italy). See: http://centridiricerca.unicatt.it/circse_index.html.

In particular, the following linguistic resources and tools for natural language processing are presented:

• Word Formation Latin: a Marie Curie IF funded project that enhances the currently available morphological analyser for Latin Lemlat (www.lemlat3.eu) with derivational morphology information;
• the Index Thomisticus Treebank: the theoretical background supporting the syntactic and semantic annotation of the syntactically annotated portion of the opera omnia of Thomas Aquinas;
• IT-VaLex and Latin Vallex: two lexica automatically induced from the Index Thomisticus Treebank. IT-VaLex provides the syntactic subcategorisation patterns of the verbs occurring in the treebank. Latin Vallex is a valency lexicon, reporting the argument frames of the valency-capable lemmas in the treebank (plus excerpts from the Latin Dependency Treebank of Classical Latin).

In the end, the talk gives an insight towards dynamic natural language processing as the most urgent challenge for addressing the problems raised by dealing with a language like Latin, which shows a wide diachronic span.