Building a knowledge graph for audit information

We present our insights from the experience of creating a knowledge graph (KG) for the auditing domain. We discuss the main challenges in building such KG starting from text and unstructured data and present an overview of our solution. The proposed approach follows a standard pipeline when it first extracts entities from auditing documents and then finds relationships among them. However, the process is especially challenging because auditing entities are in most cases non-named entities, which are hard to model in the graph and to identify in text. From our experience, we finally derive a set of observations on the limits of automatic methods for the construction of audit KGs and a possible direction to address them.