Graduate Research and Discovery Symposium (GRADS)

Caesar: A Response Retrieval System for Conversational Agents

Advisor

Larry F. Hodges

Document Type

Poster

Department

Computer Science

Publication Date

Spring 2013

Abstract

A conversational agent is a computer system capable of interacting with a human using natural language as a form of input. Conversational agents have been employed in various domains including intelligent tutoring systems, health care systems, simulation applications and user help systems. This poster presents our approach to creating intelligent conversational agents that are capable of returning appropriate responses to natural language input. Our approach consist of a support vector machine and ten different natural language processing modules used when selecting an appropriate response from the database of possible responses. When tested on a data set consisting of questions and answers for a current conversational agent project, our approach returned an accuracy score of 79.15%, a precision score of 77.58% and a recall score of 78.01%. When compared to database search we found that our approach significantly increased the number of appropriate responses returned by the system.

This document is currently not available here.

Share

COinS