@article{vanderAaLeopoldWeidlich2020,
  author    = {van der Aa, Han and Leopold, Henrik and Weidlich, Matthias},
  title     = {Partial order resolution of event logs for process conformance checking},
  series = {Decision support systems : DSS},
  volume    = {136},
  journal   = {Decision support systems : DSS},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {0167-9236},
  doi       = {10.1016/j.dss.2020.113347},
  pages     = {12},
  year      = {2020},
  abstract  = {While supporting the execution of business processes, information systems record event logs. Conformance checking relies on these logs to analyze whether the recorded behavior of a process conforms to the behavior of a normative specification. A key assumption of existing conformance checking techniques, however, is that all events are associated with timestamps that allow to infer a total order of events per process instance. Unfortunately, this assumption is often violated in practice. Due to synchronization issues, manual event recordings, or data corruption, events are only partially ordered. In this paper, we put forward the problem of partial order resolution of event logs to close this gap. It refers to the construction of a probability distribution over all possible total orders of events of an instance. To cope with the order uncertainty in real-world data, we present several estimators for this task, incorporating different notions of behavioral abstraction. Moreover, to reduce the runtime of conformance checking based on partial order resolution, we introduce an approximation method that comes with a bounded error in terms of accuracy. Our experiments with real-world and synthetic data reveal that our approach improves accuracy over the state-of-the-art considerably.},
  language  = {en}
}
@article{LeopoldvanderAaOffenbergetal.2019,
  author    = {Leopold, Henrik and van der Aa, Han and Offenberg, Jelmer and Reijers, Hajo A.},
  title     = {Using Hidden Markov Models for the accurate linguistic analysis of process model activity labels},
  series = {Information systems},
  volume    = {83},
  journal   = {Information systems},
  publisher = {Elsevier},
  address   = {Oxford},
  issn      = {0306-4379},
  doi       = {10.1016/j.is.2019.02.005},
  pages     = {30 -- 39},
  year      = {2019},
  abstract  = {Many process model analysis techniques rely on the accurate analysis of the natural language contents captured in the models' activity labels. Since these labels are typically short and diverse in terms of their grammatical style, standard natural language processing tools are not suitable to analyze them. While a dedicated technique for the analysis of process model activity labels was proposed in the past, it suffers from considerable limitations. First of all, its performance varies greatly among data sets with different characteristics and it cannot handle uncommon grammatical styles. What is more, adapting the technique requires in-depth domain knowledge. We use this paper to propose a machine learning-based technique for activity label analysis that overcomes the issues associated with this rule-based state of the art. Our technique conceptualizes activity label analysis as a tagging task based on a Hidden Markov Model. By doing so, the analysis of activity labels no longer requires the manual specification of rules. An evaluation using a collection of 15,000 activity labels demonstrates that our machine learning-based technique outperforms the state of the art in all aspects.},
  language  = {en}
}
@article{AaRebmannLeopold2021,
  author    = {Aa, Han van der and Rebmann, Adrian and Leopold, Henrik},
  title     = {Natural language-based detection of semantic execution anomalies in event logs},
  series = {Information systems : IS ; an international journal ; data bases},
  volume    = {102},
  journal   = {Information systems : IS ; an international journal ; data bases},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0306-4379},
  doi       = {10.1016/j.is.2021.101824},
  pages     = {13},
  year      = {2021},
  abstract  = {Anomaly detection in process mining aims to recognize outlying or unexpected behavior in event logs for purposes such as the removal of noise and identification of conformance violations. Existing techniques for this task are primarily frequency-based, arguing that behavior is anomalous because it is uncommon. However, such techniques ignore the semantics of recorded events and, therefore, do not take the meaning of potential anomalies into consideration. In this work, we overcome this caveat and focus on the detection of anomalies from a semantic perspective, arguing that anomalies can be recognized when process behavior does not make sense. To achieve this, we propose an approach that exploits the natural language associated with events. Our key idea is to detect anomalous process behavior by identifying semantically inconsistent execution patterns. To detect such patterns, we first automatically extract business objects and actions from the textual labels of events. We then compare these against a process-independent knowledge base. By populating this knowledge base with patterns from various kinds of resources, our approach can be used in a range of contexts and domains. We demonstrate the capability of our approach to successfully detect semantic execution anomalies through an evaluation based on a set of real-world and synthetic event logs and show the complementary nature of semantics-based anomaly detection to existing frequency-based techniques.},
  language  = {en}
}
@misc{HanvanderDiCiccioLeopoldetal.2019,
  author    = {Han van der, Aa and Di Ciccio, Claudio and Leopold, Henrik and Reijers, Hajo A.},
  title     = {Extracting Declarative Process Models from Natural Language},
  series = {Advanced Information Systems Engineering (CAISE 2019)},
  volume    = {11483},
  journal   = {Advanced Information Systems Engineering (CAISE 2019)},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-21290-2},
  issn      = {0302-9743},
  doi       = {10.1007/978-3-030-21290-2_23},
  pages     = {365 -- 382},
  year      = {2019},
  abstract  = {Process models are an important means to capture information on organizational operations and often represent the starting point for process analysis and improvement. Since the manual elicitation and creation of process models is a time-intensive endeavor, a variety of techniques have been developed that automatically derive process models from textual process descriptions. However, these techniques, so far, only focus on the extraction of traditional, imperative process models. The extraction of declarative process models, which allow to effectively capture complex process behavior in a compact fashion, has not been addressed. In this paper we close this gap by presenting the first automated approach for the extraction of declarative process models from natural language. To achieve this, we developed tailored Natural Language Processing techniques that identify activities and their inter-relations from textual constraint descriptions. A quantitative evaluation shows that our approach is able to generate constraints that closely resemble those established by humans. Therefore, our approach provides automated support for an otherwise tedious and complex manual endeavor.},
  language  = {en}
}