| Issue |
ITM Web Conf.
Volume 7, 2016
3rd Annual International Conference on Information Technology and Applications (ITA 2016)
|
|
|---|---|---|
| Article Number | 05005 | |
| Number of page(s) | 4 | |
| Section | Session 5: Algorithms and Simulation | |
| DOI | https://doi.org/10.1051/itmconf/20160705005 | |
| Published online | 21 November 2016 | |
Research on Calculation Method of Semantic Correlation of Chinese Text
Communication University of China, Dingfuzhuang NO. 1, Chaoyang District, Beijing, China
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.
© Owned by the authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.