A Novel Method for Chinese Named Entity Recognition Based on Character Vector

Jing Lu; Mao Ye; Zhi Tang; Xiao-Jun Huang; Jia-Le Ma

Collaborative Computing: Networking, Applications, and Worksharing. 11th International Conference, CollaborateCom 2015, Wuhan, November 10-11, 2015, China. Proceedings

Research Article

A Novel Method for Chinese Named Entity Recognition Based on Character Vector

Download

499 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-28910-6_13,
    author={Jing Lu and Mao Ye and Zhi Tang and Xiao-Jun Huang and Jia-Le Ma},
    title={A Novel Method for Chinese Named Entity Recognition Based on Character Vector},
    proceedings={Collaborative Computing: Networking, Applications, and Worksharing. 11th International Conference, CollaborateCom 2015, Wuhan, November 10-11, 2015, China. Proceedings},
    proceedings_a={COLLABORATECOM},
    year={2016},
    month={2},
    keywords={Named entity recognition Word vector Character vector},
    doi={10.1007/978-3-319-28910-6_13}
}

Jing Lu
Mao Ye
Zhi Tang
Xiao-Jun Huang
Jia-Le Ma
Year: 2016
A Novel Method for Chinese Named Entity Recognition Based on Character Vector
COLLABORATECOM
Springer
DOI: 10.1007/978-3-319-28910-6_13

Jing Lu^,*, Mao Ye¹^,*, Zhi Tang^,*, Xiao-Jun Huang¹, Jia-Le Ma¹

1: Peking University Founder Group Co., Ltd.

*Contact email: jing.lu@founder.com.cn, yemao.apb@founder.com.cn, 10548887@pku.edu.cn

Abstract

In this paper, a novel method using for Chinese named entity recognition is proposed. For each class, A posteriori probability model is acquired by combing probabilistic model and character vector, which are acquired from each class by using training data. After segment Chinese sentence into words, the posteriori probability of every words in each class can be calculated by using model we proposed, and thus the type of word could be determined according to maximum posteriori probability.

Keywords: Named entity recognition Word vector Character vector

Published: 2016-02-09
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-28910-6_13