Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the `how' and `why' of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the understandability of an explanation from the users' perspective. In this paper we show how ontologies help the understandability of interpretable machine learning models, such as decision trees. In particular, we build on Trepan, an algorithm that explains artificial neural networks by means of decision trees, and we extend it to include ontologies modeling domain knowledge in the process of generating explanations. We present the results of a user study that measures the understandability of decision trees in domains where explanations are critical, namely, in finance and medicine. Our study shows that decision trees taking into account domain knowledge during generation are more understandable than those generated without the use of ontologies.
The study proposes a framework of ONTOlogy-based Group Decision Support System (ONTOGDSS) for decision process which exhibits the complex structure of decision-problem and decision-group. It is capable of reducing the complexity of problem structure and group relations. The system allows decision makers to participate in group decision-making through the web environment, via the ontology relation. It facilitates the management of decision process as a whole, from criteria generation, alternative evaluation, and opinion interaction to decision aggregation. The embedded ontology structure in ONTOGDSS provides the important formal description features to facilitate decision analysis and verification. It examines the software architecture, the selection methods, the decision path, etc. Finally, the ontology application of this system is illustrated with specific real case to demonstrate its potentials towards decision-making development.
As the number and diversity of information sources on the Internet is increasing rapidly, there is an increase demand for intelligent assistants which would help people search for desired information. A number of tools are available to help people search for information on the Internet such as WW Worm (McBryan 1994), WebCrawler (Pinkerton 1994) Unfortunately, existing tools are unable to interpret the content of information resources due to the lack of knowledge. We need more intelligent systems which facilitate.
We build a mechanism to form an ontology of entities which improves a relevance of matching and searching microtext. Ontology construction starts from the seed entities and mines the web for new entities associated with them. To form these new entities, machine learning of syntactic parse trees (syntactic generalization) is applied to form commonalities between various search results for existing entities on the web. Ontology and syntactic generalization are applied to relevance improvement in search and text similarity assessment in commercial setting; evaluation results show substantial contribution of both sources to microtext processing.
Sander, Malte (Technische Universität (TU) München and Siemens AG) | Waltinger, Ulli (Siemens AG) | Roshchin, Mikhail (Siemens AG) | Runkler, Thomas (Technische Universität (TU) München and Siemens AG)
We present an implemented approach to transform natural language sentences into SPARQL, using background knowledge from ontologies and lexicons. Therefore, eligible technologies and data storage possibilities are analyzed and evaluated. The contributions of this paper are twofold. Firstly, we describe the motivation and current needs for a natural language access to industry data. We describe several scenarios where the proposed solution is required. Resulting in an architectural approach based on automatic SPARQL query construction for effective natural language queries. Secondly, we analyze the performance of RDBMS, RDF and Triple Stores for the knowledge representation. The proposed approach will be evaluated on the basis of a query catalog by means of query efficiency, accuracy, and data storage performance. The results show, that natural language access to industry data using ontologies and lexicons, is a simple but effective approach to improve the diagnosis process and the data search for a broad range of users. Furthermore, virtual RDF graphs do support the DB-driven knowledge graph representation process, but do not perform efficient under industry conditions in terms of performance and scalability.