Using deep belief nets for Chinese named entity categorization

Authors:
Yu Chen;You Ouyang;Wenjie Li;Dequan Zheng;Tiejun Zhao
Affiliations:
Harbin Institute of Technology, China;The Hong Kong Polytechnic University, Hong Kong;The Hong Kong Polytechnic University, Hong Kong;Harbin Institute of Technology, China;Harbin Institute of Technology, China
Venue:
NEWS '10 Proceedings of the 2010 Named Entities Workshop
Year:
2010

Citing 9
Cited 0

Internal and external evidence in the identification and semantic categorization of proper names

Corpus processing for lexical acquisition
Training products of experts by minimizing contrastive divergence

Neural Computation
Disambiguation of proper names in text

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Efficient support vector classifiers for named entity recognition

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Named entity recognition using an HMM-based chunk tagger

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
HowtogetaChineseName(Entity): segmentation and combination issues

EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
A fast learning algorithm for deep belief nets

Neural Computation
Detecting, categorizing and clustering entity mentions in Chinese text

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Chinese named entity recognition based on multilevel linguistic features

IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Identifying named entities is essential in understanding plain texts. Moreover, the categories of the named entities are indicative of their roles in the texts. In this paper, we propose a novel approach, Deep Belief Nets (DBN), for the Chinese entity mention categorization problem. DBN has very strong representation power and it is able to elaborately self-train for discovering complicated feature combinations. The experiments conducted on the Automatic Context Extraction (ACE) 2004 data set demonstrate the effectiveness of DBN. It outperforms the state-of-the-art learning models such as SVM or BP neural network.