Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

UC -- A Progress Report

Robert Wilensky, James Mayfield, Anthony Albert, Robert Chin, Charles Cox, Marc Luria, James H. Martin and Dekai Wu

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-87-303
July 1986

http://www.eecs.berkeley.edu/Pubs/TechRpts/1987/CSD-87-303.pdf

UC is an intelligent natural language interface that allows naive users to learn about the UNIX operating system. UC was undertaken because the task was thought to be both a fertile domain for Artificial Intelligence research and a useful application of AI work in planning, reasoning, natural language processing and knowledge representation.

The current implementation of UC comprises the following components: A language analyzer, called ALANA, that produces a representation of the content contained in an utterance; an inference component called a concretion mechanism that further refines this content; a goal analyzer, PAGAN, that hypothesizes the plans and goals under which the user is operating; an agent, called UCEgo, that decides on UC's goals and proposes plans for them; a domain planner, called UCPlanner, that computes a plan to address the user's request; an expression mechanism, UCExpress, that determines the content to be communicated to the user, and a language production mechanism, UCGen, that expresses UC's response in English.

UC also builds a model of the user that represents UC's assessment of the user's knowledge state with respect to UNIX. Another mechanism, UCTeacher, allows a user to add knowledge of both English vocabulary and facts about UNIX to UC's knowledge base. This is done by interacting with the user in natural language.

All these aspects of UC make use of knowledge represented in a knowledge representation system called KODIAK. KODIAK is a relation-oriented system that is intended to have wide representational range and a clear semantics, while maintaining a cognitive appeal. All of UC's knowledge, ranging from its most general concepts to the content of a particular utterance, is represented in KODIAK.


BibTeX citation:

@techreport{Wilensky:CSD-87-303,
    Author = {Wilensky, Robert and Mayfield, James and Albert, Anthony and Chin, Robert and Cox, Charles and Luria, Marc and Martin, James H. and Wu, Dekai},
    Title = {UC -- A Progress Report},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1986},
    Month = {Jul},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1986/6102.html},
    Number = {UCB/CSD-87-303},
    Abstract = {UC is an intelligent natural language interface that allows naive users to learn about the UNIX operating system. UC was undertaken because the task was thought to be both a fertile domain for Artificial Intelligence research and a useful application of AI work in planning, reasoning, natural language processing and knowledge representation.  <p>  The current implementation of UC comprises the following components: A language analyzer, called ALANA, that produces a representation of the content contained in an utterance; an inference component called a concretion mechanism that further refines this content; a goal analyzer, PAGAN, that hypothesizes the plans and goals under which the user is operating; an agent, called UCEgo, that decides on UC's goals and proposes plans for them; a domain planner, called UCPlanner, that computes a plan to address the user's request; an expression mechanism, UCExpress, that determines the content to be communicated to the user, and a language production mechanism, UCGen, that expresses UC's response in English.  <p>  UC also builds a model of the user that represents UC's assessment of the user's knowledge state with respect to UNIX. Another mechanism, UCTeacher, allows a user to add knowledge of both English vocabulary and facts about UNIX to UC's knowledge base. This is done by interacting with the user in natural language.  <p>All these aspects of UC make use of knowledge represented in a knowledge representation system called KODIAK. KODIAK is a relation-oriented system that is intended to have wide representational range and a clear semantics, while maintaining a cognitive appeal. All of UC's knowledge, ranging from its most general concepts to the content of a particular utterance, is represented in KODIAK.}
}

EndNote citation:

%0 Report
%A Wilensky, Robert
%A Mayfield, James
%A Albert, Anthony
%A Chin, Robert
%A Cox, Charles
%A Luria, Marc
%A Martin, James H.
%A Wu, Dekai
%T UC -- A Progress Report
%I EECS Department, University of California, Berkeley
%D 1986
%@ UCB/CSD-87-303
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1986/6102.html
%F Wilensky:CSD-87-303