A Hybrid Approach for Chinese Named Entity Recognition

Authors:
Xiaoshan Fang;Huanye Sheng
Affiliations:
-;-
Venue:
DS '02 Proceedings of the 5th International Conference on Discovery Science
Year:
2002

Citing 3
Cited 1

A maximum entropy approach to named entity recognition

A maximum entropy approach to named entity recognition
Automatic acquisition of hyponyms from large text corpora

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Projecting corpus-based semantic links on a thesaurus

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics

Named entity recognition for Vietnamese

ACIIDS'10 Proceedings of the Second international conference on Intelligent information and database systems: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Handcrafted rule based systems attain a high level of performance but constructing rules is a time consuming work and low frequency patterns are easy to be neglected. This paper presents a hybrid approach, which combines a machine learning method and a rule based method, to improve our Chinese NE system's efficiency. We describe a bootstrapping algorithm that extracts patterns and generates semantic lexicons simultaneously. After the use of new patterns 14% more person names are extracted by our system.