Chinese Named Entity Recognition via Joint Identification and Categorization

ZHOU Junsheng; QU Weiguang; ZHANG Fen

Article Contents

Article Navigation > Chinese Journal of Electronics > 2013 > 22(2): 225-230

ZHOU Junsheng, QU Weiguang, ZHANG Fen, “Chinese Named Entity Recognition via Joint Identification and Categorization,” Chinese Journal of Electronics, vol. 22, no. 2, pp. 225-230, 2013,

Citation:

ZHOU Junsheng, QU Weiguang, ZHANG Fen, “Chinese Named Entity Recognition via Joint Identification and Categorization,” Chinese Journal of Electronics, vol. 22, no. 2, pp. 225-230, 2013,

ZHOU Junsheng, QU Weiguang, ZHANG Fen, “Chinese Named Entity Recognition via Joint Identification and Categorization,” Chinese Journal of Electronics, vol. 22, no. 2, pp. 225-230, 2013,

Citation:

ZHOU Junsheng, QU Weiguang, ZHANG Fen, “Chinese Named Entity Recognition via Joint Identification and Categorization,” Chinese Journal of Electronics, vol. 22, no. 2, pp. 225-230, 2013,

PDF( 197 KB)

Chinese Named Entity Recognition via Joint Identification and Categorization

1.
Jiangsu Research Center of Information Security and Privacy Technology, Nanjing 210046, China;
2.
School of Computer Science and Technology, Nanjing Normal University, Nanjing 210046, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61073119) and the Jiangsu Natural Science Foundation of China (No.BK2010547).

Received Date: 2012-04-01
Rev Recd Date: 2012-07-01
Publish Date: 2013-04-25

Abstract

Abstract

Chinese Named entity recognition (NER) is an important task for Chinese information processing. Traditional sequence labeling approaches to Chinese NER cannot treat globally a string of continuous characters as a named entity candidate so that the entity-level features cannot be exploited in a natural way. To deal with this problem, we formulate Chinese NER as a joint identification and categorization task that performs the two subtasks simultaneously: boundary identification and entity categorization, together with segmentation. The proposed approach provides a natural formulation to treats pieces of continuous characters as named entity candidates, which allows for more accurate prediction by examining both the internal evidence and contextual information of the candidates. Within this framework, we explored a variety of effective feature representations for Chinese NER. Closed tests on two quite different corpora from the third SIGHAN bakeoff show that our approach significantly outperforms the best in the literature, achieving state-of-theart performance.
- Named entity recognition,
- Entity-level features,
- Sequence labeling approach,
- Joint identification and categorization

FullText(HTML)

References(16)

References

Gina-Anne Levow, "The third international Chinese language processing bakeoff: Word segmentation and named entity recognition", Proc. of the Fifth SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, pp.108-117, 2006.

H. Zhang, Q. Liu, H.K. Yu, Y.Q. Cheng and S. Bai, "Chinese named entity recognition using role model", Computational Linguistics and Chinese Language Processing, Vol.8, No.2, pp.29-60, 2003.

W. Chen, Yujie Zhang and Hitoshi Isahara, "Chinese named entity recognition with conditional random fields", Proc. of 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, pp.118-121, 2006.

J. Zhou, L. He, X. Dai and J. Chen, "Chinese named entity recognition with a multiphase model", Proc. of 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, pp.213-216, 2006.

A. Chen, F. Peng, R. Shan and G. Sun, "Chinese named entity recognition with conditional probabilistic models", Proc. of 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, pp.173-176, 2006.

J. Lafferty, A. McCallum and F. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data", Proc. of ICML, San Francisco, USA, pp.282- 289, 2001.

Yue Zhang and Stephen Clark, "Joint word segmentation and POS tagging using a single perceptron", Proc. of ACL/HLT, Columbus, OH, pp.888-896, 2008.

Yue Zhang and Stephen Clark, "A fast decoder for joint word segmentation and POS-tagging using a single discriminative model", Proc. of EMNLP, Cambridge, MA, pp.843-852, 2010.

W. Jiang, Haitao Mi and Qun Liu, "Word lattice reranking for Chinese word segmentation and part-of-speech tagging", Proc. of COLING, Manchester, UK, pp.385-392, 2008.

Canasai Kruengkrai, Kiyotaka Uchimoto, Jun'ichi Kazama et al., "An error-driven word-character hybrid model for joint Chinese word segmentation and POS tagging", Proc. of ACL/AFNLP, Suntec, Singapore, pp.513-521, 2009.

Michael Collins, "Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms", Proc. of EMNLP, Philadelphia, USA, pp.1-8, 2002.

Michael Collins and Brian Roark, "Incremental parsing with the perceptron algorithm", Proc. of 42nd ACL, Barcelona, Spain, pp.111-118, 2004.

Richard Sproat, Chilin Shih, William Gale and Nancy Chang, "A stochastic finite-state word-segmentation algorithm for Chinese", Computational Linguistics, Vol.22, No.3, pp.377-404, 1996.

Pavel Pecina, "Lexical association measures and collocation extraction", Language Resources and Evaluation, Vol.44, No.1-2, pp.137-158, 2010.

G. Zhou and J. Su, "Named entity recognition using an HMMbased chunk tagger", Proc. of the 40th ACL, Philadelphia, USA, pp.473-480, 2002.

Andrew McCallum, Wei Li, "Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons", Proc. of the Seventh CoNLL Conference, Edmonton, pp.188-191, 2003.

Relative Articles

Supplements(0)

Cited By

Proportional views