Knowledge-based conversational agents and virtual storytelling

Abstract. We describe an architecture for building speech-enabled conversational agents, deployed as self-contained Web services, with ability to provide inference processing on very large knowledge bases and its application to voice enabled chatbots in a virtual storytelling environment. The architecture integrates Prolog based natural language pattern matching components and story specific information extraction from RDF/XML files. Our Web interface is dynamically generated by server side agents supporting multi-modal interface components (speech and animation). Prolog refactorings of the WordNet lexical knowledge base, FrameNet and the Open Mind common sense knowledge repository are combined with internet meta-search to provide high-quality knowledge sources to our conversational agents. An example of conversational agent with speech capabilities is deployed on the Web at http://logic.csci.unt.edu:8080/wordnet_agent/frame.html.

• Type: Conference
• Year: 2004
• Where: SAC
• Authors: Paul Tarau, Elizabeth Figa
• Keywords: Applied Computing, Conversational Agent, Knowledge Base, SAC 2004, Speech-enabled Conversational Agents