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 inference engines, 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. The agent is also accessible for live multi-user text-based chat, through a Yahoo Instant Messenger protocol adaptor, from wired or wireless devices, as the jinni_agent Yahoo IM "handle".

REFERENCES

• 1: Collin F. Baker , Charles J. Fillmore , John B. Lowe, The Berkeley FrameNet Project, Proceedings of the 17th international conference on Computational linguistics, August 10-14, 1998, Montreal, Quebec, Canada
• 2: Marc Cavazza , Fred Charles , Steven J. Mead, Characters in Search of an Author: AI-Based Virtual Storytelling, Proceedings of the International Conference on Virtual Storytelling: Using Virtual Reality Technologies for Storytelling, p.145-154, September 27-28, 2001
• 3: Patrick Cousot , Radhia Cousot, Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints, Proceedings of the 4th ACM SIGACT-SIGPLAN symposium on Principles of programming languages, p.238-252, January 17-19, 1977, Los Angeles, California [doi>10.1145/512950.512973]
• 4: C. Felbaum. Wordnet, an Electronic Lexical Database for English. Cambridge: MIT Press, 1998.
• 5: Clive Fencott, Virtual Storytelling as Narrative Potential: Towards an Ecology of Narrative, Proceedings of the International Conference on Virtual Storytelling: Using Virtual Reality Technologies for Storytelling, p.90-99, September 27-28, 2001
• 6: E. Figa and P. Tarau. Story Traces and Projections: Exploring the Patterns of Storytelling. In N. Braun and U. Spierling, editors, TIDSE'2003, Darmstadt, Germany, Mar. 2003.
• 7: E. Figa and P. Tarau. The VISTA Project: An Agent Architecture for Virtual Interactive Storytelling. In N. Braun and U. Spierling, editors, TIDSE'2003, Darmstadt, Germany, Mar. 2003.
• 8: A. A. foundation. Artificial Intelligence Markup Language (AIML). Technical report, 2001. Available at http://alice.sunlitsurf.com/TR/2001/WD-aiml/.
• 9: D. Gildea and D. Jurafsky. Automatic labeling of semantic roles, 2002.
• 10: M. Mateas and A. Stern. Integrating Plot, Character and Natural Language Processing in the Interactive Drama Facade. In N. Braun and U. Spierling, editors, Proceedings of the Technologies for Interactive Digital Storytelling and Entertainment Conference, Darmstadt, Germany, Mar. 2003.
• 11: Microsoft. The Microsoft Agent Home Page. http://www.microsoft.com/msagent.
• 12: G. Miller, R. Beckwith, C. Fellbaum, D. Gross, and K. Miller. Five papers on WordNet. CSL Report 43, Cognitive Science Laboratory, Princeton University, July 1990.
• 13: P. Singh. The public acquisition of commonsense knowledge. In Proceedings of AAAI Spring Symposium on Acquiring (and Using) Linguistic (and World) Knowledge for Information Access, Palo Alto, California, 2002. AAAI.
• 14: P. Singh. The Open Mind Common Sense. Technical report, M.I.T. Media Lab, 2003. http://commonsense.media.mit.edu.
• 15: P. Tarau. Inference and Computation Mobility with Jinni. In K. Apt, V. Marek, and M. Truszczynski, editors, The Logic Programming Paradigm: a 25 Year Perspective, pages 33--48. Springer, 1999. ISBN 3-540-65463-1.
• 16: Paul Tarau, Fluents: A Refactoring of Prolog for Uniform Reflection an Interoperation with External Objects, Proceedings of the First International Conference on Computational Logic, p.1225-1239, July 01, 2000
• 17: P. Tarau. The Jinni 2003 Prolog Compiler: a High Performance Java and .NET based Prolog for Object and Agent Oriented Internet Programming. Technical report, BinNet Corp., 2003. URL: http://www.binnetcorp.com/Jinni.
• 18: P. Tarau and V. Dahl. A Logic Programming Infrastructure for Internet Programming. In M. J. Wooldridge and M. Veloso, editors, Artifical In telligence Today- Recent Trends and Developmnts, pages 431--456. Springer, LNAI 1600, 1999. ISBN 3--540--66428--9.
• 19: Paul Tarau , Veronica Dahl, High-level networking with mobile code and first order AND-continuations, Theory and Practice of Logic Programming, v.1 n.3, p.359-380, May 2001 [doi>10.1017/S1471068401001193]
• 20: P. Tarau, K. De Boschere, V. Dahl, and S. Rochefort. LogiMOO: an Extensible Multi-User Virtual World with Natural Language Control. Journal of Logic Programming, 38(3):331--353, Mar. 1999.
• 21: R. Wallace. AIML Pattern Matching Simplified. Techinical report, A.L.I.C.E. AI foundation, 2002. Available at http://alice.sunlitsurf.com/documentation/matching.html.
• 22: M. Zancanaro, A. Cappelletti, and C. Signorino. Interactive Storytelling: People, Stories, and Games. In Proceedings of the International Conference on Virtual Storytelling, Avignon, France, Sept. 2001.

INDEX TERMS

Keywords:
FrameNet and Open Mind-based knowledge processing, WordNet, agent architectures, agentbased Web services, conversational agents, logic programming, natural language and speech processing, virtual storytelling