2017 IEEE International Conference on Big Knowledge (ICBK) (2017)
Hefei, Anhui, China
Aug. 9, 2017 to Aug. 10, 2017
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICBK.2017.56
It is necessary to unify data from different sources in Web information fusion as the same entity has different expressions in the real world. People usually use the information obtained from the search engine to make decisions in daily life. The idea of decision-making by means of search engines' information is used for synonymous entity recognition. In this paper, we propose a method of synonymous entity recognition based on feature fusion, which used multiplicative information fusion technique to fuse multi-results of synonymous entity recognition. In order to utilize the information obtained from the search engine, we combine entity name and other entity features as query words and design a new similarity function VarSim to measure entities' similarity. The F-score of algorithm on the basis of feature fusion on the two datasets are 13.42% and 1.81% higher than that of the recognition method on the basis of the entity name, which demonstrates the effectiveness of the synonymous entity recognition approach using feature fusion.
Search engines, Feature extraction, Web search, Algorithm design and analysis, Hospitals, Fuses, Mathematical model
D. Cai, J. He, G. Wu and X. Hu, "Synonymous Entity Recognition Based on Feature Fusion," 2017 IEEE International Conference on Big Knowledge (ICBK), Hefei, Anhui, China, 2017, pp. 161-166.