Automatic Classification of Geographical Named Entities

Daniel Ferrés (1), Marc Massot (2), Muntsa Padró (1), Horacio Rodríguez (1), Jordi Turmo (1)

(1) Talp Research Center, Universitat Politècnica de Catalunya, C/ Jordi Girona 1-3 - 08034 Barcelona, Spain {dferres,mpadro,turmo,horacio}@lsi.upc.es; (2) Dept. Informàtica i Matemàtica Aplicada, Universitat de Girona, Edifici P4, Campus Montilivi, 17071 Girona, Spain. marc@ima.udg.es

P24-T

Performing accurate Named Entity (NE) classification (NEC) has recently become a central issue in many NLP applications, such as Information Extraction and Question Answering, among others. Most state-of-the-art NEC systems use coarse-grained MUC-style datasets for performing the NEC task reducing it to distinguish among LOCATION, PERSON, ORGANIZATION and so. There is, however, a growing interest on using finer-grained classification sets. This paper describes a methodology that applies Machine Learning techniques for a finer-grained classification of NEs that have been previously classified as locations by a NERC system.

NE subclassification, named entities, geographical named entities, machine learning, inductive logic programming.

237.pdf