Magazine article AI Magazine

Report on the Fourth International Conference on Knowledge Capture (K-CAP 2007)

Magazine article AI Magazine

Report on the Fourth International Conference on Knowledge Capture (K-CAP 2007)

Article excerpt

The Knowledge Capture 2007 (K-CAP 2007) Conference was held in Whistler, British Columbia (Canada), October 28-31, 2007. This was the fourth in a series of meetings; the first was held in Victoria, British Columbia, in 2001; the second was collocated with the ISWC meeting and was held on Sanibel Island, Florida, in October 2003; and the third meeting was held in Banff, Alberta, in October 2005. The conference was held at the Fairmont Chateau in Whistler. Whistler is a spectacular setting and is one of the principal sites of the 2010 Winter Olympic Games. Views from the conference hotel were breathtaking, and many of the participants took advantage of the venue to participate in various forms of outdoor sports.

The topics covered in the invited talks, technical papers, posters, and demonstrations included knowledge engineering and modeling methodologies, knowledge engineering and the semantic web, mixed-initiative planning and decision-support tools, acquisition of problem-solving knowledge, knowledge-based markup techniques, knowledge extraction systems, knowledge acquisition tools, and advice-taking systems.

Many of the presentations touched upon the special relationship that knowledge capture and knowledge engineering currently have with the semantic web, as the web is seen as a resource that can be exploited by knowledge capture techniques; and in turn the resulting knowledge-based systems can enhance the web environment.

The first day of the conference featured a series of focused and lively workshops. These events, which were organized by John Gennari (University of Washington), featured workshops titled Semantic Authoring, Annotation, and Knowledge Markup; the Second International Workshop on Modular Ontologies; Knowledge Capture and Constraint Programming; and Knowledge Management and Semantic Web for Engineering Design.

The topics of the two invited talks covered different aspects of innovative approaches to knowledge capture. As Derek Sleeman noted in his introductory comments, knowledge capture is now a "broad church" that includes "traditional" knowledge engineer-expert dialogues, PSM-directed (problem-solving method) knowledge acquisition systems such as MOLE, SALT, and OPAL/Protege, as well as machine-learning approaches. In the last decade or so, knowledge capture has again expanded its horizons significantly to embrace information-extraction techniques, and more recently the web and enhanced connectivity have led to further significant developments. We are of course referring to systems like OpenMind where many ordinary users answer a range of questions about commonsense topics such as What is the main emotion you feel on your birthday? Alternatively, such users are asked to complete paragraphs or sentences. Statistical techniques are then used to extract information from the sizeable bodies of data produced. Both these exciting topics were featured as the two invited talks.

The first invited talk by Oren Etzioni (University of Washington, Seattle), "Everything I Know I Learned from Google: Machine Reading of Web Text," argued lucidly that information-extraction (natural languageprocessing) techniques have matured to the point where they can be used as very effective knowledge-capture tools. Further, Etzioni showed how this work has been influenced by, and has taken advantage of, the web, which of course contains a vast number of text-based documents.

The second invited talk at this K-CAP was engagingly presented by Luis von Ahn (Carnegie Mellon University, Pittsburgh); he spoke on the cuttingedge topic of extracting information from web-based game-playing systems. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.