TraceWalk: Semantic-based Process Graph Embedding for Consistency Checking
This addresses the issue of low accuracy and poor adaptability in open-domain PCC for business process management, representing a first attempt using deep learning in this interdisciplinary field.
The paper tackles the problem of process consistency checking (PCC) by introducing TraceWalk, a deep learning method that uses semantic-based process graph embeddings to predict consistencies between graphical and textual descriptions, achieving higher accuracy than state-of-the-art baselines.
Process consistency checking (PCC), an interdiscipline of natural language processing (NLP) and business process management (BPM), aims to quantify the degree of (in)consistencies between graphical and textual descriptions of a process. However, previous studies heavily depend on a great deal of complex expert-defined knowledge such as alignment rules and assessment metrics, thus suffer from the problems of low accuracy and poor adaptability when applied in open-domain scenarios. To address the above issues, this paper makes the first attempt that uses deep learning to perform PCC. Specifically, we proposed TraceWalk, using semantic information of process graphs to learn latent node representations, and integrates it into a convolutional neural network (CNN) based model called TraceNet to predict consistencies. The theoretical proof formally provides the PCC's lower limit and experimental results demonstrate that our approach performs more accurately than state-of-the-art baselines.