This paper evaluates a wide range of heterogeneous semantic similarity measures on the task of predicting semantic similarity scores and the task of predicting semantic relations that hold between two terms, and investigates ways to combine these measures. We present a large-scale benchmarking of 34 knowledge-, web-, corpus-, and definition-based similarity measures. The strengths and weaknesses of each approach regarding relation extraction are discussed. Finally, we describe and test two techniques for measure combination. These combined mea- sures outperform all single measures, achieving a correlation of 0.887 and Precision(20) of 0.979.
Panchenko, A. (2012). A Study of Heterogeneous Similarity Measures for Semantic Relation Extraction. JEP-TALN-RECITAL 2012, volume 3: RECITAL, Grenoble, France. https://hdl.handle.net/2078.5/159960