Explanations in knowledge systems: design for explainable expert systems

Abstract. Policies are pervasive in web applications. They play crucial roles in enhancing security, privacy and usability of distributed services. There has been extensive research in the area, including the Semantic Web community, but several aspects still exist that prevent policy frameworks from widespread adoption and real world application. This paper discusses important requirements and open research issues in this context, focusing on policies in general and their integration into trust management frameworks, as well as on approaches to increase system cooperation, usability and user-awareness of policy issues.

Section: Cooperative Policy Enforcementmentioning

confidence: 99%

Semantic Web Policies – A Discussion of Requirements and Research Issues

Bonatti

Duma

Fuchs

et al. 2006

“…For example, expert systems researchers understood the need for systems that understood their reasoning processes and could generate explanations in a language understandable to its users [SHORT76]. A more detailed description about requirements and the necessity of answer explanation components can be found in [McG96], literature on explanations for expert systems [SWA91], theorem proving explanations [FeMi87] or [BOY95].…”

Section: Answer Justificationmentioning

confidence: 99%

Ontology-Based Query and Answering in Chemistry: OntoNova Project Halo

Angele¹,

Moench²,

Oppermann³

et al. 2003

Abstract. The Project Halo has the long term objective of developing a Digital Aristotle, i.e. a knowledge system that is able to answer questions in a particular domain and give explanations for its answers. In this paper we report about the Ontoprise contribution to the Halo Pilot Project, in which various competing ontology engineering methodologies and knowledge system capabilities have been investigated. Concerning the first, we describe how we dealt with engineering a significant set of laws from chemistry that we had to let interact at different levels of generality and in varying orders. With regard to the latter, we report on the ability of our system to produce coherent and concise explanations of its reasoning. The importance of these two aspects can hardly be underestimated in the Semantic Web, as with future growth the interaction of large sets of laws will require dedicated management as well as the ability to let the user explore the trustworthiness of the ontology and the underlying data sources.

“…For example, from the early days in expert systems (e.g., MYCIN [18]), expert systems researchers identified the need for systems that understood their reasoning processes and could generate explanations in a language understandable to its users. Inference Web attempts to stand on the shoulders of past work in expert systems, such as MYCIN and the Explainable Expert System [20] on generating explanations.…”

Section: Background and Related Workmentioning

confidence: 99%

Infrastructure for Web Explanations

McGuinness

Silva

2003

Abstract. The Semantic Web lacks support for explaining knowledge provenance. When web applications return answers, many users do not know what information sources were used, when they were updated, how reliable the source was, or what information was looked up versus derived. The Semantic Web also lacks support for explaining reasoning paths used to derive answers. The Inference Web (IW) aims to take opaque query answers and make the answers more transparent by providing explanations. The explanations include information concerning where answers came from and how they were derived (or retrieved). In this paper we describe an infrastructure for IW explanations. The infrastructure includes: an extensible web-based registry containing details on information sources, reasoners, languages, and rewrite rules; a portable proof specification; and a proof and explanation browser. Source information in the IW registry is used to convey knowledge provenance. Representation and reasoning language axioms and rewrite rules in the IW registry are used to support proofs, proof combination, and semantic web agent interoperability. The IW browser is used to support navigation and presentations of proofs and their explanations. The Inference Web is in use by two Semantic Web agents using an embedded reasoning engine fully registered in the IW. Additional reasoning engine registration is underway in order to help provide input for evaluation of the adequacy, breadth, and scalability of our approach.