A simple rule-based approach to organization name recognition in Chinese text

Abstract

This paper presents a simple rule based approach to organization name recognition in Chinese text. Based on Chinese knowledge sources, our approach detects potential left and right boundaries in a text, and then determines whether a left-right boundary pair encloses an organization name by using a length constraint and non-organization name words/POS-tag constraints. Organization names with nested structure are also processed. This approach is easy to implement and the evaluation results are satisfactory. © Springer-Verlag Berlin Heidelberg 2005.