A maximum entropy approach to named entity recognition
A maximum entropy approach to named entity recognition
Named entity recognition: a maximum entropy approach using global information
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Hi-index | 0.00 |
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.