A Document Feature Extraction Method Based on Concept-Word List

Abstract:

When describing a document in Vector Space Model (VSM), it often assumes that there is no semantic relationship between words or they are orthogonal to each other. In order to improve the inaccurate document description, a new document description method has been proposed in this paper by introducing a concept-word, which calculates the semantic similarity between words based on HowNet ontology database. Comparative experiments show that the new method can not only improve effectively the effect of document feature description in VSM, but also reduce significantly the dimension of a document vector. The research is very useful to document clustering, query word expansion in Web information retrieval and personalized service in e-business applications.

• Periodical: Advanced Materials Research (Volume 267)
• Pages: 386-392
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.267.386
• Online since: June 2011
• Authors: Zheng Yu Zhu, Jie He, Shu Jia Dong, Chun Lei Yu
• Keywords: Concept-Word, Document Feature Extraction, HowNet, Vector Space Model

References

[1] Z.L. Jiang, X.K. Xu and S. Li: Feature extraction of text classification based on word clustering. Journal of Harbin Engineering University. Vol. 11(2008), pp.1205-1209.

[2] Y. Wang, M. Zhang and L. Ma: Text categorization based on word aggregation and decision tree. Journal of Hebei University(Natural Science Edition). Vol. 03(2005), pp.338-342.

[3] L. Zhao, T. Hu, X.J. Huang et al.: Hownet-based conceptual feature selection method. Journal of China Institute of Communications. Vol. 07(2004), pp.46-54.

[4] Q. Liu and S.J. Li: Word similarity computing based on how-net. Computational Linguistics and Chinese Language Processing. Vol. 7(2002), pp.59-76.

[5] Information on http: /www. ictclas. org.

[6] J.J. Sun and Y. Cheng: Technology of information retrieval. Science Press. pp.166-167. (2004).

[7] Information on http: /download. csdn. net/source/1987618.

[8] Information on http: /www. pudn. com/downloads91/sourcecode/chinese/detail348916. html.