A new algorithm of rule generation for Chinese information extraction

Author

Wang, Jinghua ; Liu, Jianyi

Author_Institution

CISTR, Beijing Univ. of Posts & Telecommun., China

fYear

2005

fDate

30 Oct.-1 Nov. 2005

Firstpage

565

Lastpage

570

Abstract

Learning rules automatically is a hot and difficult topic in information extraction. This paper proposes an algorithm for rule generation in Chinese information extraction - RGA-CIE, which is domain independent for free text of Chinese. RGA-CIE applies supervised learning with bottom-up strategy, which is a rule generalization process with a heuristic method to decide rule generalization path and Laplacian* formula to evaluate the performance of rules. The learned rules have been applied to the experimental system-CHES (comprehensive information based Chinese information extraction system), and achieved good result, which proves the feasibility and effectiveness of RGA-CIE.

Keywords

information retrieval; learning (artificial intelligence); natural languages; Chinese information extraction system; Laplacian formula; RGA-CIE algorithm; comprehensive information; heuristic method; rule generation algorithm; supervised learning; system-CHES; Buildings; Data mining; Dictionaries; Information resources; Laplace equations; Machine learning; Robustness; Supervised learning; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Language Processing and Knowledge Engineering, 2005. IEEE NLP-KE '05. Proceedings of 2005 IEEE International Conference on

Print_ISBN

0-7803-9361-9

Type

conf

DOI

10.1109/NLPKE.2005.1598801

Filename

1598801