Design and Development of a Named Entity Recognizer for an Agglutinative Language

This paper presents the conclusions reached from the development of a system for Named Entity recognition in written Basque. The system was designed in four steps: first, the development of a recognizer based on linguistic information represented on finitestate-transducers; second, the generation of semi-automatically annotated corpora from the result of these transducers; third, the achievement of the best possible recognizer by training different ML techniques on these corpora; and finally, the combination of the different recognizers obtained. Being Basque an agglutinative language, a linguistic preprocess previous to these steps was required.