home · mobile · calendar · defenses · 1996-1997 · 

Thesis Defense - Jones

Spoken-Language Help for High-Functionality Applications
Michael Jones
Computer Science PhD Candidate
5/28/1997
10:00am-12:00pm

Modern, high-functionality computer applications are difficult to learn and use. Users of these applications frequently need help to complete their work. However, traditional keyword-based help systems are awkward to use and they frequently fail to satisfy their users' information needs. Allowing users to ask for help in their own words offers a more natural interaction than provided by keyword systems. Analysis of the language used in the questions facilitates the successful retrieval of answers at a far superior rate.

This dissertation describes SAGE, a help system that has been developed by combining techniques gleaned from the information retrieval (IR) and artificial intelligence (AI) communities. SAGE handles users' questions by retrieving answers from an existing collection of help text. The kernel of SAGE is based on an advanced IR technique called Latent Semantic Indexing (LSI). This kernel is then enhanced by the addition of robust natural language processing and machine learning techniques.

Both the development and evaluation of SAGE have been empirical efforts. Live user studies with a simulated system were used to gather data crucial to the design of the system. Evaluation of the system was based on relevance judgments for a set of naturally occurring queries and on live user studies.

The results of these evaluations indicate that the SAGE approach can be quite effective when deployed in realistic settings. In particular, the SAGE results have shown that given unconstrained natural language questions, answers to users' information needs can be retrieved from existing help text.

Committee: James Martin, Associate Professor (Chair)
Clayton Lewis, Professor
Elizabeth Jessup, Assistant Professor
Thomas Landauer, Department of Psychology
Daniel Jurafsky, Assistant Professor
Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
webmaster@cs.colorado.edu
www.cs.colorado.edu
May 5, 2012 (14:20)
XHTML 1.0/CSS2
©2012