Research on Calculation Method of Semantic Correlation of Chinese Text

• Main Authors: Li Yan-Fang, Sun Shu-Tao, Feng Shuang, Wang Qi
• Format: Article
• Language: English
• Published: EDP Sciences 2016-01-01
• Series: ITM Web of Conferences
• Online Access: http://dx.doi.org/10.1051/itmconf/20160705005

The semantic correlation is a very important research direction in Natural Language Processing, and the semantic relatedness is different from the semantic similarity . At present, the semantic correlation algorithm, which is based on the similarity of the semantic meaning, and it can’t achieve the desired results in a certain extent. In this paper, byusing the large-scale corpus and How Net words’ concepts to dig out the hidden semantic relations between the words, finally, according to the semantic relations of the words in the text, the text correlation algorithm is proposed . Experimental results show that the use of How Net calculation of the text relevance which use less time than the use of large-scale corpus and Tongyici Cilin calculation of the text relevance, and in terms of accuracy of the calculation results also have to upgrade.