Measuring semantic similarity between words using lexical knowledge and neural networks

Li, Y; Bandar, Z; Mclean, D

Abstract

This paper investigates the determination of semantic similarity by the incorporation of structural semantic knowledge from a lexical database and the learning ability of neural networks. The lexical database is assumed to be organised in a hierarchical structure. The extracted lexical knowledge contains the relative location of the concerned words in the lexical hierarchy. The neural network then processes available lexical knowledge to provide semantic similarity for words. Experimental evaluation against a benchmark set of human similarity ratings demonstrates that the proposed method is effective in measuring semantic similarity between words.

Citation

Li, Y., Bandar, Z., & Mclean, D. (2002). Measuring semantic similarity between words using lexical knowledge and neural networks. In H. Yin, N. Allinson, R. Freeman, J. Keane, & S. Hubbard (Eds.), Intelligent Data Engineering and Automated Learning — IDEAL 2002 : Third International Conference Manchester, UK, August 12–14, 2002 Proceedings (111-116). Springer Berlin Heidelberg. https://doi.org/10.1007/3-540-45675-9_19

• Publication Date: Aug 1, 2002
• Deposit Date: Jul 6, 2015
• Pages: 111-116
• Series Title: Lecture Notes in Computer Science
• Series Number: 2412
• Book Title: Intelligent Data Engineering and Automated Learning — IDEAL 2002 : Third International Conference Manchester, UK, August 12–14, 2002 Proceedings
• ISBN: 9783540440253
• DOI: https://doi.org/10.1007/3-540-45675-9_19
• Publisher URL: http://dx.doi.org/10.1007/3-540-45675-9_19
• Related Public URLs: http://link.springer.com/book/10.1007/3-540-45675-9