Resolución de Correferencia de Nombres de Persona para Extracción de Información Biográfica

Information extraction systems need a previous processing step in order to recognize coreferential elements, such as personal name variants. This paper has two aims: the first is to describe the main types of personal name coreference found in encyclopedic and journalistic texts in Spanish. Furthermore, we introduce an algorithm that solves most coreferential links between personal name variants succesfully. The system, which does not need a training corpus, unifies the coreferential elements found in a text, thereby improving tasks like biographical information extraction.