Abstract. Process model matching refers to the automatic identification of corresponding activities between two process models. It represents the basis for many advanced process model analysis techniques such as the identification of similar process parts or process model search. A central problem is how to evaluate the performance of process model matching techniques. Often, not even humans can agree on a set of correct correspondences. Current evaluation methods, however, require a binary gold standard, which clearly defines which correspondences are correct. The disadvantage of this evaluation method is that it does not take the true complexity of the matching problem into account and does not fairly assess the capabilities of a matching technique. In this paper, we propose a novel evaluation method for process model matching techniques. In particular, we build on the assessment of multiple annotators to define probabilistic notions of precision and recall. We use the dataset and the results of the Process Model Matching Contest 2015 to assess and compare our evaluation method. We find that our probabilistic evaluation method assigns different ranks to the matching techniques from the contest and allows to gain more detailed insights into their performance.
Process model matching refers to the automatic identification of corresponding activities between two process models. It represents the basis for many advanced process model analysis techniques such as the identification of similar process parts or process model search. A central problem is how to evaluate the performance of process model matching techniques. Current evaluation methods require a binary gold standard that clearly defines which correspondences are correct. The problem is that often not even humans can agree on a set of correct correspondences. Hence, evaluating the performance of matching techniques based on a binary gold standard does not take the true complexity of the matching problem into account and does not fairly assess the capabilities of a matching technique. In this paper, we propose a novel evaluation procedure for process model matching techniques. In particular, we build on the assessments of multiple annotators to define the notion of a non-binary gold standard. In this way, we avoid the problem of agreeing on a single set of correct correspondences. Based on this non-binary gold standard, we introduce probabilistic versions of precision, recall, and F-measure as well as a distance-based performance measure. We use a dataset from the Process Model Matching Contest 2015 and a total of 16 matching systems to assess and compare the insights that can be obtained by using our evaluation procedure. We find that our probabilistic evaluation procedure allows us to gain more detailed insights into the performance of matching systems than a traditional evaluation based on a binary gold standard.
Abstract. Process model matching refers to the automatic detection of semantically equivalent or similar activities between two process models. The output of process model matchers is the basis for many advanced process model analysis techniques and, therefore, must be as accurate as possible. Measuring the performance of process model matchers, however, is a difficult task. On the one hand, it is hard to define which correspondences are actually correct. On the other hand, it is challenging to appropriately take the output of matchers into account, because they often produce confidence values between zero and one. In this paper, we propose the first evaluation procedure for process model matchers that addresses both of these challenges. The core idea is to rank both the computed and the desired correspondences based on their confidence values and compare them using the Spearman's rank correlation coefficient. We perform an in-depth evaluation in which we apply the new evaluation procedure and illustrate how it helps gaining interesting insights.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.