Application of MCL in a dialog agent

We report on a natural language agent, originally developed as a command driven interface, that was enhanced with time-dependence, contradiction tolerance, meta-linguistic abilities, and an overall meta-cognitive awareness. We show how these new capacities together can make an AI system’s natural language processing more robust and human-like.

[1]  Stuart C. Shapiro.  SNePS: a logic for natural language understanding and commonsense reasoning , 2000 .

[2]  Hesham Khalil.  Logical foundations of reactive default reasoning , 2002, DISKI.

[3]  Stuart C. Shapiro,et al.  Book Reviews: Natural Language Processing and Knowledge Representation: Language for Knowledge and Knowledge for Language , 2001, CL.

[4]  Tim Oates,et al.  The metacognitive loop I: Enhancing reinforcement learning with metacognitive monitoring and control for improved perturbation tolerance , 2006, J. Exp. Theor. Artif. Intell..

[5]  Wolfgang Bibel,et al.  Let's Plan It Deductively! , 1997, IJCAI.

[6]  Tim Oates,et al.  Toward Domain-Neutral Human-Level Metacognition , 2007, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning.

[7]  Ashok K. Goel,et al.  Using Model-Based Reflection to Guide Reinforcement Learning , 2005 .

[8]  J. C. Boudreaux,et al.  The Role of language in problem solving 2 : edited proceedings of the Johns Hopkins University Applied Physics Laboratory Second Symposium on the Role of Language in Problem Solving held in Laurel, Maryland, 2-4 April, 1986 , 1987 .

[9]  Eleni Stroulia,et al.  Failure-driven learning as model-based self-redesign , 1994 .

[10]  Donald Perlis,et al.  Reasoning situated in time I: basic concepts , 1990, J. Exp. Theor. Artif. Intell..

[11]  David B. Leake.  Experience, introspection and expertise: Learning to refine the case-based reasoning process , 1996, J. Exp. Theor. Artif. Intell..

[12]  Donald Perlis,et al.  Conversational adequacy: mistakes are the essence , 1998, Int. J. Hum. Comput. Stud..

[13]  Tim Oates,et al.  Ontologies for Reasoning about Failures in AI Systems , 2007 .

[14]  James A. Hendler,et al.  Readings in Planning , 1994 .

[15]  Donald Perlis,et al.  Systems that detect and repair their own mistakes , 2001 .

[16]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[17]  Ronald J. Brachman,et al.  (AA)AI More than the Sum of Its Parts , 2006, AI Mag..

[18]  Chung Hee Hwang,et al.  The TRAINS project: a case study in building a conversational planning agent , 1994, J. Exp. Theor. Artif. Intell..