Combining taxonomy-based semantic similarity methods and fuzzy similarity methods

This dataset presents the results of an experiment evaluating an approach for measuring similarity between two terms by combining taxonomy-based semantic similarity measures with fuzzy similarity measures.
Six taxonomy-based — SimR [1], SimW&P [2], SimL [3], SimJ&C [4], SimP&S [5], SimA [6] — were enhanced using three fuzzy similarity measures inspired by the Jaccard index [7], the Dice coefficient, and cosine similarity [8].
The original taxonomy-based methods and their enhanced versions have been experimented with four datasets, MC30 [9], RG65 [10], WordSim-353 [11], and Simlex-999 [12].
The results indicate that Pearson's correlation coefficients with human judgments exceed those obtained using the original versions of each of the six methods, regardless of the fuzzy similarity measure applied. The greatest improvements are achieved when the six methods are refined using cosine similarity. Specifically, the average performance gains range from 0.026 for SimJ&C to 0.093 for SimA.

[1] Resnik P. Using Information Content to Evaluate Semantic Similarity in a Taxonomy. In Proc. of the Int. Joint Conf. on Artificial Intelligence, Montreal, Quebec, Canada, August 20-25, Morgan Kaufmann, 448-453, 1995.
[2] Wu Z., Palmer M. Verb semantics and lexical selection. In Proc. of the 32nd Annual Meeting of the Associations for Computational Linguistics, Las Cruces, New Mexico, 133-138, 1994.
[3] Lin, D. An Information-Theoretic Definition of Similarity. In Proceedings of the Int. Conf. on Machine Learning, Madison, Wisconsin, USA. Morgan Kaufmann, 296-304, 1998.
[4] Jiang, J.J., Conrath, D.W. Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy. In Proc. of Inter. Conf. Research on Computational Linguistics (ROCLING X), Taiwan, 1997.
[5] Pirrò, G. A Semantic Similarity Metric Combining Features and Intrinsic Information Content. Data Knowl. Eng, 68(11), 1289-1308, 2009.
[6] Adhikari, A., Singh, S., Mondal, D., Dutta, B., Dutta, A. A Novel Information Theoretic Framework for Finding Semantic Similarity in WordNet. CoRR, arXiv:1607.05422, abs/1607.05422, 2016.
[7] Formica A. Similarity reasoning in formal concept analysis: from one-to many-valued contexts. Knowledge and Information Systems, 60(2):715–739, 2019.
[8] Zimmermann H-J. Fuzzy Set Theory — and Its Applications. Springer, 2001.
[9] Miller G.A., Charles W.G. Contextual correlates of semantic similarity. Language and Cognitive Processes 6(1), 1-28, 1991.
[10] Rubenstein H. and Goodenough J. B. Contextual correlates of synonymy. Communications of the ACM, 8(10):627–633, 1965.
[11] Finkelstein L., Gabrilovich E., Matias Y., Rivlin E., Solan Z., Wolfman G., and Ruppin E.. Placing search in context: the concept revisited. In Proc of the 10th Int. Conf. on World Wide Web, WWW ’01, page 406–414, New York, NY, USA, 2001.
[12] Hill F., Reichart R., Korhonen A. SimLex-999: Evaluating semantic models with (genuine) similarity estimation. Computational Linguistics, 41(4):665–695, 2015.