Explainable Adaptive Assistants

Printer-friendly version


Usable adaptive assistants need to be able to explain their recommendations if users are expected to trust them. Our work on ICEE -- the Integrated Cognitive Explanation Environment -- provides an extensible infrastructure for supporting explanations. We aim to improve trust in learning-enabled agents by providing transparency concerning:
  • Provenance
  • Information manipulation
  • Task processing
  • Learning
The ICEE explainer includes:
  • Descriptions of question types and explanation strategies
  • Architecture for generating interoperable, machine interpretable, sharable justifications of answers containing enough information to generate explanations
  • Components capable of obtaining justification information from SPARK (a BDI agent architecture)
  • History of execution states as justifications


DateCreated ByLink
March 14, 2013
Patrick WestDownload
March 14, 2013
Patrick WestDownload

Related Projects:

Inference Web Project LogoInference Web
Principal Investigator: Deborah L. McGuinness
Description: The Inference Web is a Semantic Web based knowledge provenance infrastructure that supports interoperable explanations of sources, assumptions, learned information, and answers as an enabler for trust. Provenance - if users (humans and agents) are to use and integrate data from unknown, uncertain, or multiple sources, they need provenance metadata for evaluation Interoperability - more systems are using varied sources and multiple information manipulation engines, thus increasing interoperability requirements Explanation/Justification - if information has been manipulated (i.e., by sound deduction or by heuristic processes), information manipulation trace information should be available Trust - if some sources are more trustworthy than others, trust ratings are desired The Inference Web consists of two important components: Proof Markup Language (PML) Ontology - Semantic Web based representation for exchanging explanations including provenance information - annotating the sources of knowledge justification information - annotating the steps for deriving the conclusions or executing workflows trust information - annotating trustworthiness assertions about knowledge and sources IW Toolkit - Web-based and standalone tools that facilitate human users to browse, debug, explain, and abstract the knowledge encoded in PML.

Related Research Areas:

Inference And Trust
Lead Professor: Deborah L. McGuinness
Description: Inference And Trust
Concepts: Semantic Web
Web Science
Lead Professor: Jim Hendler, Deborah L. McGuinness
Description: Web Science is the study of the World Wide Web and its impact on both society and technology, positioning the Web as an object of scientific study unto itself. Web Science recognizes the Web as a transformational, disruptive technology; its practitioners study the Web, its components, facets and characteristics. Ultimately, Web Science is about understanding the Web and anticipating how it might evolve in the future.
Concepts: Semantic Web