Istituto di Linguistica Computazionale
CHLT LEMLAT is going to be a computational instrument for the morphological analysis
of the Latin, whose results are compatible with the requirements of the project CHLT.
In order to obtain it, we are developing new functionalities of an existing version of
LEMLAT (first version of 1992, developed jointly by ILC- CNR and University of Torino).
This new version will be called CHLT LEMLAT. When the first version of LEMLAT receives
in input a word form, this latter is segmented into its formative elements and a
corresponding lemma is produced in output, with respective code that indicates the
flexive paradigm.The lexical base of LEMLAT is the result of the collation of the
following three dictionaries: Georges, Gradenwitz and Oxford Latin Dictionary.
The last one is the main reference.
Particularly, our aim is to enrich the output
of LEMLAT, adding some new morphological information such as case, gender, number....
The results of CHLT LEMLAT analysis can be used, for instance, in fields such as
linguistics and literary research, didactics and information retrieval.
The use of such an instrument is fundamental for management of whichever lexical patrimony.
At the end of the work, CHLT LEMLAT will operate a complete morphological lemmatization of
the input texts and words.