GraSM

GraSM (Graph-based Similarity Measure) is a method for incorporating the semantic richness of a graph in semantic similarity measures by selecting disjunctive common ancestors of two concepts. GraSM assumes that two common ancestors are disjunctive if there are independent paths from both ancestors to the concept. In 2011, the authors of GraSM proposed the method DiShIn with a higher computational efficiency and a more solid management of parallel interpretations.

Example

For example, palladium, platinum and gold are considered to be precious metals, and gold and copper considered to be coinage metals. Thus, we have:

                   metal
                  /     \
           precious     coinage
         /     |    \    /  \
palladium  platinum  gold   copper

When calculating the semantic similarity between platinum and gold, most topological measures only use their most informative common ancestor, in this case precious. On the other hand, GraSM takes also in account the following independent paths to metal:

gold -> coinage -> metal 
platinum -> precious -> metal

Thus, GraSM defines the similarity between platinum and gold proportional to the average of the information content of their common disjunctive ancestors: metal and precious; and the similarity between platinum and palladium only proportional to the information content of precious, since there are no independent paths from them to metal.

This means that for GraSM palladium and platinum are more similar than platinum and gold, since gold can have another interpretation.

References

• Couto, F. & Silva, M. (2011), Disjunctive Shared Information between Ontology Concepts: application to Gene Ontology. Journal of Biomedical Semantics, 2:5
• Couto, F., Silva, M., & Coutinho, P. (2007). Measuring semantic similarity between Gene Ontology terms. Data and Knowledge Engineering, 61:137–152
• Couto, F., Silva, M., & Coutinho, P. (2005). Semantic similarity over the gene ontology: Family correlation and selecting disjunctive ancestors. In Proc. Of the ACM Conference in Information and Knowledge Management (CIKM)