Research in Knowledge Acquisition
Research in Ontologies and Problem-Solving Methods
Research in Planning
Research in Multi-Agent Communication and Coordination
We are working on several areas to enhance and extend EXPECT's current knowledge acquisition capabilities.
1. Exploting Interdependecy Models
EXPECT analyzes the interdependencies among individual pieces of knowledge and generates an Interdependency Model (IM). This model determines what additional knowledge needs to be acquired and thus what are the remaining KA tasks that the user must do. The baseline EXPECT system uses an agenda mechanism as a useful way to guide users during KA. The agenda shows the user what KA tasks remain to be done based on the IM and on different types of errors in the KB that EXPECT detects automatically, and guides the user to resolve them with the KA tools.
2. Script-Based KA
We are developing a new approach to KA based on the use of KA Scripts that capture typical knowledge base modification sequences. Our tool uses these KA scripts to help users make changes to a knowledge base. We have a principled set of dimensions to organize and populate our library of KA Scripts. Several evaluations have been performed with this tool.
3. English-based Knowledge Acquisition
We are interested in developing tools that enable users to specify new knowledge in natural language, so that they are more accessible to end users. We have developed an interface that allows users to modify methods by manipulating their paraphrase in English. It allows the user to select a portion of the paraphrase that corresponds to a valid expression and picking from a menu of suggestions for other expressions that can be used to replace it. Generating sensible suggestions is one of the challenging aspects of this work.
4. Support in creating new KBs
There is not much knowledge at the beginning to form expectations for KA, but a KA tool can create more expectations as the user enters knowledge. This tool tries to help a user create a KB without errors before the problem solver is run. The tool builds expectations based on the representation language (includes a method editor with adaptive forms), based on surface interdependencies (as opposed to the deeper interdependencies detected by the problem solver), and based on a restricted language for users to specify KA constraints and tasks. Preliminary evaluations with users show a 30% improvement in terms of the time to complete a KB modification.
5. Experimental Methodology for Evaluating KA Tools
We are performing pioneering work in knowledge acquisition concerning the evaluation of KA tools and approaches. EXPECT's KA tools are already instrumented to collect several kinds of information during a KA session, including times when users execute KA modifications, what kind of modification is done, what pending KA tasks remain according to EXPECT's analysis of the knowledge base, what new knowledge was added and what and how existing knowledge was changed, etc.