Abstract—Named entity recognition involves processing of texts to identify and classify entities such as names of person, place, organization, etc. In this study, a system for a named entity recognizer for Filipino texts using support vector machine was developed, and its performance was evaluated and compared to an existing named entity recognizer intended for the same language, but uses a rule-based approach. Based from the results, the named entity recognizer using support vector machine performed best in tagging named entity class date with 95.52% f-measure, achieving 84.97% overall f-measure.
Index Terms—Information extraction, named entity recognition, natural language processing, support vector machine
C. M. Castillo, M. A. L. Mateo, A. D. C. Paras, and V. D. F. Santos are currently undergraduate students from the College of Computer Management and Information Technology, Polytechnic University of the Philippines (e-mail: jona_lyne1224@yahoo.com, marck.augustus.mateo@gmail.com, gigabyte_paras@yahoo.com, vinadanica0430@yahoo.com).
R. A. Sagum is with the faculty of the College of Computer Management and Information Technology of the Polytechnic University of the Philippines (e-mail: riasagum31@yahoo.com)
[PDF]
Cite: Jonalyn M. Castillo, Marck Augustus L. Mateo, Antonio D. C. Paras, Ria A. Sagum, and Vina Danica F. Santos, "Named Entity Recognition Using Support Vector Machine for Filipino Text Documents," International Journal of Future Computer and Communication vol. 2, no. 5, pp. 530-532, 2013.