Measuring Semantic Similarity Between Words Using Lexical Knowledge and Neural Networks
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.
KeywordsSemantic Similarity Word Pair Short Path Length Human Rating Lexical Database
Unable to display preview. Download preview PDF.
- 1.Budanitsky, A., Hirst, G., Semantic Distance in WordNet: An Experimental, Application-Oriented Evaluation of Five Measures. Workshop WordNet and other Lexical Resources, North American Chapter of the Assoc. for Computational Linguistics. Pittsburgh, 2001.Google Scholar
- 4.Jiang, J.J., Conrath, D.W., Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy. Proc. ROCLING X. Taiwan, 1997.Google Scholar
- 5.Lin, D., An Information-Theoretic Definition of Similarity. Proc. Int’l Conf. Machine Learning. Madison, Wisconsin, 1998.Google Scholar
- 6.McHale, M., A Comparison of WordNet and Roget’s Taxonomy for Measuring Semantic Similarity. Proc. COLING/ACL Workshop, 1998.Google Scholar
- 11.Richardson, R., Smeaton, A.F., Murphy, J., Using WordNet as a Knowledge Base for Measuring Semantic Similarity. Working Paper CA-1294, Dublin City Univ., 1994.Google Scholar