论文信息 - Text similarity calculation method based on ontology model

Text similarity calculation method based on ontology model

Chinese text similarity calculation plays an important role in the Chinese information processing field. This paper uses ontology to calculate text similarity. The ontology has been widely used in natural language processing. Its unique concept model on the relationship offers a new processing method for word similarity calculation. Based on the characteristics of ontology and combined with HowNet and TongYiCi CiLin, we design a Hybrid Word Similarity Calculation-HWSC method and present a text similarity calculation method based on ontology model. The experimental results show that the method can make full use of the characteristics of ontology to accurately calculate the similarity between two texts.

Lizhen Liu | Wei Song | Chao Du | Hanshi Wang | Tao Chi

[1] W. Bruce Croft,et al. Similarity measures for tracking information flow , 2005, CIKM '05.

[2] Cheng-Teh James Huang,et al. Logical Relations in Chinese and the Theory of Grammar , 1998 .

[3] Yuefeng Li,et al. A Personalized Ontology Model for Web Information Gathering , 2011, IEEE Transactions on Knowledge and Data Engineering.

[4] P. Shrestha,et al. Corpus-Based methods for Short Text Similarity , 2011, JEPTALNRECITAL.

[5] Philip Resnik,et al. Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language , 1999, J. Artif. Intell. Res..

[6] Ted Pedersen,et al. Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

[7] Zhao Wei. Words Similarity Algorithm Based on Tongyici Cilin in Semantic Web Adaptive Learning System , 2010 .

[8] Tang Da-quan. Word’s semantic similarity computation method based on Hownet , 2010 .

[9] R GruberThomas. Toward principles for the design of ontologies used for knowledge sharing , 1995 .