Gryphon is a dialogue system designed to allow a user to get information about available courses through a natural language input interface and a bimodal speech-text output. It incorporates several open source technologies as leverage to accomplish this daunting task. These technologies provided a framework through which a non-linear, multi-stage, system was created to perform the above task. This document provides an overview of the system components from a technical perspective, with particular attention paid to the transformational aspects of each module from input to output. It is designed to portray the system in a manner that is as straight-forward as possible.
The problem that we faced is a common one in today's world: magnitude of information outweighs organization. When registering for a course at Carleton College ,in Northfield Minnesota, it often proves difficult to find all the information you need about a specific course or type of course. Gryphon not only contains a relatively complete database of course information for the fall 2003 trimester, but it offers this information in a unique way. Gryphon accepts natural language queries in the form of speech and text and provides responses as speech and text as well.
This site is intended for both the user and the programmer. For the user there is a README file that shows usage and sample conversations, along with a brief synopsis of the types of queries that can be made.
For the programmer, there are several pages with pertinant information about downloading and using the different components. This includes how to manipulate the system to use data other than the Carleton College Fall 2004 course database.
There is also a manifesto describing the components and their roles in the dialogue system. Along with this is a powerpoint show which visualizes these roles. For best performance, it is recommended to use a Mac to view it.
Finally, we have our compressed files themselves, including the database.
Here is the site map: