engleski

Implementation of Croatian NERC system

In this paper a system for Named Entity Recognition and Classification in Croatian language is described. The system is com-posed of the module for sentence segmen-tation, inflectional lexicon of common words, inflectional lexicon of names and regular local grammars for automatic rec-ognition of numerical and temporal expres-sions. After the first step (sentence segmen-tation), the system attaches to each token its full morphosyntactic description and appropriate lemma and additional tags for potential categories for names without dis-ambiguation. The third step (the core of the system) is the application of a set of rules for recognition and classification of named entities in already annotated texts. Rules based on described strategies (like internal and external evidence) are applied in cas-cade of transducers in defined order. Al-though there are other classification sys-tems for NEs, the results of our system are annotated NEs which are following MUC-7 specification. System is applied on infor-mative and noninformative texts and results are compared. F-measure of the system ap-plied on informative texts yields over 90%.

named entity recognition and classification; Croatian; computational linguistics; information extraction

nije evidentirano