A tagger environment for Galician

Abstract

[Abstract] In this paper, we introduce a tagger environment for Galician, the native language of Galicia. Galician belongs to the group of Romance languages which developed from the Latin imposed on the north-west of the Iberian Peninsula by the Romans, with additions from the languages of peoples living here before the colonization, as well as contributions from other languages subsequent to the breaking-up of the Roman Empire.

Various historical circumstances led to its not becoming a State language and although it was relegated to informal usage, our vernacular has managed to survive well into the twentieth century when, parallel to the recovery of the institutions for self-government, Galician was once again granted the status of official language for Galicia, together with the Spanish language.

From an operational point of view, our proposal is based on the notion of finite automaton, separating the execution strategy from the implementation of the tagging interpreter. That facilitates the maintenance at the time that assures the robustness of the architecture. Empirical tests prove the validity of our approach to deal with a language whose morphology is non-trivial.