|
|
| A Reflective Architecture for Knowledge Acquisition | |
Description
Our research focus is the development of acquisition interfaces that help users to extend the knowledge of intelligent systems and their knowledge bases.
You may want to browse our old EXPECT Web pages that contain lots of pointers and details about our work on EXPECT from 1992-2002.
Main Research Themes
Our work concentrates on several research themes nad are motivated by a number of user studies that we have conducted:- How do users know they are doing the right thing? When a system understands how each individual piece of knowledge relates to others then it can figure out how new knowledge fits, and can figure out how to interact with the user when new knowledge is inconsistent or when other necessary knowledge is missing. Our approach is to build acquisition interfaces that can automatically derive Interdependency Models from a knowledge base and use them to guide the acquisition dialogue. We used this approach in EMeD (EXPECT's Method Editor), and in the KANAL tools for analyzing process models.
- How can we help users handle the formal representations that our systems use? Building on past research on natural language generation, we have developed an English-based editor that allows users to select meaningful strings of a paraphrase and search the knowledge base for sensible alternative replacements.
- How can we help users make complex modifications to a knowledge base that require many related small changes? We have developed dialogue planning tools that represent typical sequences of changes that users make and use them to dynamically generate follow-up questions to users. We used this approach in KA Scripts, PSMTool/Constable, and our new work on acquisition dialog planning.
- How can we help users figure out where to start? Because it is hard for users to start entering knowledge from scratch, we assume that the system has some general background knowledge that the user populates with domain-specific information. We have built several declarative domain theories for this purpose, including PLANET (a PLAn semantic NET).
- How can a user turn informal and possibly disconnected information into increasingly more formalized and operational knowledge?
Application Areas
Our research is motivated by real applications, which often revolve around planning and process models:- knowledge acquisition for planning and process models: PSMTool/Constable, KANAL, Pathway Assembly
- plan evaluation and user preferences: PSMTool/Constable, KANAL,
- plan representation and ontologies: grammars and ontologies for air campaign planning objectives, PLANET (a PLAn semantic NET), SADL (SHAKEN Action Description Language)
- bioinformatics: KANAL
- special operations: TEMPLE
- competitive and military intelligence: TRELLIS
- earthquake science, in collaboration with the Southern California Earthquake Center (SCEC): Pathway Assembly
- air campaign planning: INSPECT, JDP,
- logistics: EXPECT, INSPECT,
Research Collaborations
Our projects are funded by larger funding programs and often result in multi-site collaboration and integration efforts, including:- Rapid Knowledge Formation (RKF) and High Performance Knowledge Bases (HPKB)
- Active Templates (AcT)
- Control of Agent-Based Systems (CoABS)
- DARPA / Rome Planning Initiative (ARPI), under the Planning and Decision Aids (PDA) program.
- Joint Defense Planner (JDP) and Joint Forces Air Component Commander (JFACC) programs
- National Science Foundation Information Technology Research