CATCG: a general purpose parsing tool applied

Alex Alsina (Universitat Pompeu Fabra)

Toni Badia (Universitat Pompeu Fabra)

Gemma Boleda (Universitat Pompeu Fabra)

Stefan Bott (Universitat Pompeu Fabra)

Àngel Gil (Universitat Pompeu Fabra)

Martí Quixal (Universitat Pompeu Fabra)

Oriol Valentín (Universitat Pompeu Fabra)

WP3: Tools & Components

This paper focuses on the language processing tool being developed at our centre and briefly describes two of its applications. CATCG, our morphosyntactic analyser, is designed to deal with general written Catalan text. In CATCG the whole processing task has been divided into specific subtasks and for each one of them we try to apply the best strategy available. The most relevant properties of our system are its robustness, the fact that we have given reusability a very high priority, and the goal of acquiring linguistic information by fully automatic means.
The paper is structured as follows: section 1 and 2 explicate and describe the global architecture of CATCG. Section 3 shows the output of CATCG and gives data on its performance. Section 4 describes two projects to which CATCG is being applied: BancTrad and PrADo. Section 5 presents our plans for future work. Section 6 closes the paper with some conclusions.

NLP, Shallow parser, Constraint grammar, Tagging, catalan

106.pdf