IMPORTANT: This is the moodle page for the 2019-2020 edition of the Computational Linguistics course (12 CFU) that has  been replaced by LMJ070-1 and LMJ070-2 (6 CFU each).

This course aims at providing students with both an understanding of the methodological foundations of Computational Linguistics along with an hands-on training on the basic techniques for the computational annotation and analysis of written text. It is structured in two modules.

The first module focuses on the theoretical and methodological foundation of the automatic treatment of Natural Language. Students will be introduced to the formal basis of Language Theory, to the automatic and manual annotation of corpora and their use for linguistic research. The monographic part of the course will focus on the computational representation of lexical meaning, and particular attention will be given to vector-based representations (distributional semantics).

The second module provides students with the basic technical skills for the computational analysis of written data, especially text corpora. No theoretical issues will be discussed, rather basic tools and techniques will be covered. Most of the work involves writing simple programs in the Python programming language in order to manage textual documents, search and annotate them, extract frequencies and other statistics, etc.