Semantic chunks segmentation based on maximum entropy model

doi:10.3778/j.issn.1002-8331.2009.26.035

Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (26): 118-120.DOI: 10.3778/j.issn.1002-8331.2009.26.035

• 数据库、信息处理 • Previous Articles Next Articles

Semantic chunks segmentation based on maximum entropy model

XIE Fa-kui^1,2，ZHANG Quan²

1.Graduate University of Chinese Academy of Sciences，Beijing 100039，China
2.Institute of Acoustics，Chinese Academy of Sciences，Beijing 100190，China

Received:2008-05-19 Revised:2008-08-12 Online:2009-09-11 Published:2009-09-11
Contact: XIE Fa-kui

基于最大熵模型的语义块切分

谢法奎^1,2，张全²

1.中国科学院研究生院，北京 100039
2.中国科学院声学研究所，北京 100190

通讯作者: 谢法奎

Abstract

Abstract: Semantic chunks segmentaion is an important task in the Hierarchical Network of Concepts（HNC） theory.To deal with this problem，this paper adopts a new method based on statistical modeling.And forms some feature templates with word，POS，concept，and selects features by a incremental way.Finally，construct a semantic chunks segmentation system based on a maximum entropy model.The experiment is taken on HNC corpus，and the result shows that the model works well，the open test precision and recall are 83.78% and 91.17% respectively.

Key words: maximum entropy model, sematic chunk, Hierarchical Network Concepts（HNC）

摘要： 语义块切分是HNC理论的重要课题，与以往的处理策略不同，采用统计建模的方法来解决这一问题。采用词语、词性、概念等信息组成特征模板，并应用增量方法进行特征选择，构建了一个基于最大熵模型的语义块切分系统。在HNC标注语料库上的测试取得了较好的效果，开放测试的正确率和召回率分别达到了83.78%和91.17%。

关键词: 最大熵模型, 语义块, 概念层次网络

CLC Number:

TP391

XIE Fa-kui^1,2，ZHANG Quan². Semantic chunks segmentation based on maximum entropy model[J]. Computer Engineering and Applications, 2009, 45(26): 118-120.

谢法奎^1,2，张全². 基于最大熵模型的语义块切分[J]. 计算机工程与应用, 2009, 45(26): 118-120.

[1]	XIA Wuji1，2, HUAQUE Cairang1. Research of tibetan personal pronouns anaphora resolution based on mixed strategy [J]. Computer Engineering and Applications, 2018, 54(7): 66-69.
[2]	LIU Ying, WANG Nan. Comparison of clause alignment based on maximum entropy model and Back Propagation neural network model [J]. Computer Engineering and Applications, 2015, 51(7): 112-117.
[3]	SANG Haiyan1，2, Gulia·Altenbek1，2, NIU Ningning1，2. Kazakh part-of-speech tagging method based on maximum entropy [J]. Computer Engineering and Applications, 2013, 49(11): 126-129.
[4]	Guljamal Mamateli1，Askar Rozi2，Askar Hamdulla1. Hybrid algorithm of polyphonic word disambiguation in Uyghur language [J]. Computer Engineering and Applications, 2011, 47(35): 158-160.
[5]	CAO Bo,SU Yi-dan,DENG Qi. Automatic recognition of Chinese name based on maximum entropy [J]. Computer Engineering and Applications, 2009, 45(4): 227-228.
[6]	LI Ru^1，2，SONG Xiao-xiang¹，WANG Wen-jing¹. Chinese question classification based on Chinese FrameNet [J]. Computer Engineering and Applications, 2009, 45(31): 111-114.
[7]	FANG Wei^1,2,HUANG Li^1,2,CUI Zhi-ming^1,2. Automatic identifying query interfaces of deep Web with maximum entropy classifier [J]. Computer Engineering and Applications, 2008, 44(21): 133-137.
[8]	LI Jun-hui,LI Pei-feng,ZHU Qiao-ming,QIAN Pei-de. Email categorization with maximum entropy model [J]. Computer Engineering and Applications, 2007, 43(35): 126-129.
[9]	,,,. Research on Mail Filtering System based on Maximum Entropy Model [J]. Computer Engineering and Applications, 2006, 42(32期): 0-.

Semantic chunks segmentation based on maximum entropy model

基于最大熵模型的语义块切分

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 9

Recommended Articles

Metrics