Abstract：Chinese semantic annotation aims to find out the senses of a multi-semantic word,which is widely applied in
natural language processing. This paper proposes a novel approach for semantic annotation of multi-semantic Chinese nouns. Given a multi-semantic Chinese noun,the proposed method can get its senses. The procedure is described as follows. The search results including URLs and abstracts of related Web pages are acquired through a search engine. The initial semantic classes are automatically generated by an online URL classifier using information gotten at the first step. Clustering algorithms are adopted to make full use of the Web page abstracts to get the final semantic classes. Experimental results demonstrate the proposed novel approach can obtain a considerable precision and recall rate with little manual intervention.
参考文献
[ 1 ] Gabrilovich E,Markovitch S. Computing Semantic Relatedness
Using Wikipedia-based Explicit Semantic Analysis[
C] / / Proc. of International Joint Conference on Artificial
Intelligence. Hydrabad, India: [ s. n. ], 2007:
1606-1611.
[ 2 ] De Saeger S, Kazama J, Torisawa K, et al. A Web
Service for Automatic Word Class Acquisition [ C] / /
Proc. of the 3rd International Universal Communication
Symposium. Tokyo,Japan:ACM Press,2009:132-138.
[ 3 ] Pasca M. Acquisition of Categorized Named Entities for
Web Search[C] / / Proc. of the 13th ACM International
Conference on Information and knowledge Management.
Washington D. C. ,USA:ACM Press,2004:137-145.
[ 4 ] Shi Shuming,Liu Xiaokang,Wen Jirong. Pattern-based
Semantic Class Discovery with Multi-membership Support[
C] / / Proc. of the 17th ACM Conference on Information
and Knowledge Management. Napa Valley, USA:ACM Press,2008:1453-1454.
[ 5 ] Arora R,Ravindran B. Latent Dirichlet Allocation Based
Multi-document Summarization [C] / / Proc. of the 2nd
Workshop on Analytics for Noisy Unstructured Text
Data. Singapore:ACM Press,2008:91-97.
[ 6 ] Li Fang,Shen Huiyu,He Tingting. Tag-topic Model for
Semantic Knowledge Acquisition from Blogs [ C ] / /
Proc. of the 7th International Conference on Natural
Language Processing and Knowledge Engineering.
[S. l. ]:IEEE Press,2011:221-226.
[ 7 ] 何婷婷,李 芳. 基于主题模型的博客标签语义知识
获取[J]. 中国通信,2012,9(3):38-48.
[ 8 ] Liu Yang, He Tingting, Tu Xinhui, et al. Obtaining
Chinese Semantic Knowledge from Online Encyclopedia
[ C ] / / Proc. of International Conference on Natural
Language Processing and Knowledge Engineering.
[S. l. ]:IEEE Press,2010:1-7.
[ 9 ] Baykan E, Henzinger M, Marian L, et al. A
Comprehensive Study of Features and Algorithms for
URL-based Topic Classification[J]. ACM Transactions
on the Web,2011,5(3).
[10] Devi M I, Rajaram D R, Selvakuberan K. Machine
Learning Techniques for Automated Web Page
Classification Using URL Features [ C ] / / Proc. of
International Conference on Computational Intelligence
and Multimedia Applications. [ S. l. ]: IEEE Press,
2007:116-120.
[11] Baykan E,Henzinger M,Marian L,et al. Purely URLbased
Topic Classification [ C ] / / Proc. of the 18th
International Conference on World Wide Web. [S. l. ]: ACM Press,2009:1109-1110.
[12] 张 宇,宋 巍,刘 挺,等. 基于URL 主题的查询分
类方法[ J ]. 计算机研究与发展, 2012, 49 (6):
1298-1305.
[13] 张 宇,宋 巍,谢毓彬,等. 利用URL 类别改进查询
主题分类[C] / / 第六届全国信息检索学术会议论文
集. 哈尔滨:哈尔滨工业大学出版社,2010:157-166.
编辑 顾逸斐
