The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - July/August (2009 vol.24)
pp: 59-67
Nicholas L. Cassimatis , Rensselaer Polytechnic Institute
ABSTRACT
Systems with human-level intelligence must be both flexible and able to reason in an appropriate time scale. These two goals are in tension, as manifested by the contrasting properties of general inference algorithms and structured knowledge-based systems. The problem of resolving ambiguous, implicit, and nonliteral references exemplifies many of these difficulties. We describe an approach, called reasoned unification, for dealing with these challenges by representing and jointly reasoning over linguistic and nonlinguistic knowledge (including structures such as scripts and frames) within the same inference framework. Reasoned unification enables a treatment of several reference resolution phenomena that to our knowledge have not previously been the subject of a unified analysis. This analysis illustrates how reasoned unification can resolve many difficult problems with using complex knowledge structures while maintaining their benefits.
INDEX TERMS
IEEE intelligent systems, human-level intelligence, artificial intelligence, natural language
CITATION
Nicholas L. Cassimatis, "Flexible Inference with Structured Knowledge through Reasoned Unification", IEEE Intelligent Systems, vol.24, no. 4, pp. 59-67, July/August 2009, doi:10.1109/MIS.2009.73
REFERENCES
1. J.R. Hobbs et al., "Interpretation as Abduction," tech. note 499, Artificial Intelligence Center, SRI International, 1990.
2. M. McShane, "Reference Resolution Challenges for Intelligent Agents: The Need for Knowledge," IEEE Intelligent Systems, vol. 24, no. 4, 2009, pp. 47–58.
3. J. Pustejovsky, The Generative Lexicon, MIT Press, 1995.
4. G. Nunberg, "The Non-Uniqueness of Semantic Solutions: Polysemy," Linguistics and Philosophy, vol. 3, no. 1, 1979, pp. 143–184.
5. R. Mitkov et al., "A New Fully Automatic Version of Mitkov's Knowledge-Poor Pronoun Resolution Method," Computational Linguistics and Intelligent Text Processing, LNCS 2276, Springer, 2002, pp. 69–83.
6. N.L. Cassimatis, "A Cognitive Substrate for Human-Level Intelligence," Artificial Intelligence Magazine, vol. 27, no. 2, 2006, pp. 45–56.
7. N.L. Cassimatis, "Polyscheme: A Cognitive Architecture for Integrating Multiple Representation and Inference Schemes," doctoral dissertation, Media Lab, Massachusetts Inst. of Technology, 2002.
8. N.L. Cassimatis, "Grammatical Processing Using the Mechanisms of Phy-sical Inferences," Proc. 26th Ann. Conf. Cognitive Science Soc., Lawrence Erlbaum Associates, 2004, pp. 192–197.
9. A. Murugesan and N.L. Cassimatis, "A Model of Syntactic Parsing Based on Domain-General Cognitive Mechanisms," Proc. 28th Ann. Conf. Cognitive Science Soc. (CogSci 06), Cognitive Science Soc., 2006, pp. 1,850–1,855.
10. N.L. Cassimatis et al., "An Architecture for Adaptive Algorithmic Hybrids," Proc. 22nd Conf. Artificial Intelligence (AAAI 07), AAAI Press, 2007, pp. 1,520–1,526.
11. H. Clark, Using Language, Cambridge Univ. Press, 1996.
12. B. Milch et al., "BLOG: Probabilistic Models with Unknown Objects," Proc. Int'l Joint Conf. Artificial Intelligence (IJCAI 05), IJCAI, 2005, pp. 1,352–1,359.
13. N. Cassimatis, A. Murugesan, and P. Bignoli, "Inference with Relational Theories over Infinite Domains," Proc. 22nd Int'l FLAIRS Conf. (FLAIRS 09), AAAI Press, 2009.
18 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool