CS7341 Conceptual Information Processing
Prof. Janet L. Kolodner
Spring, 1999
How can we explain understanding? Reasoning? Access to knowledge? Application of knowledge for understanding, reasoning, and learning? These are big questions, and we certainly can’t answer them in one 10-week course. We can, however, learn an approach to answering them and learn a piece of the history of research aimed at answering them. That’s what we’ll do in this course. We’ll follow the progression of a stream of research at the edges of artificial intelligence and cognitive science that addressed, and continues to address, these questions. The stream descends from Roger Schank’s landmark work in the early 70’s trying to find primitive symbols that one might use to represent the meaning of what we read and hear (Conceptual Dependency) and trying to define processes that could interpret sentences and paragraphs to extract their meaning (Conceptual Analysis). We’ll go through the exercises that group went through and ask the same questions, leading us down the road through the work of Schank’s group at Yale through 1985 and addressing issues in knowledge representation, reasoning that aims toward understanding, organizing knowledge in a long-term memory for easy access, and the application of memory’s knowledge in understanding. We’ll then follow some of the paths that work opened up in defining a new type of expert system (case-based reasoning) and approaches to explanation and learning.
There will be a considerable amount of reading required in this course as well as periodic assignments and a final exam. There may be some programming, but not major programming.
The required text, at the bookstore is Schank and Abelson, Scripts, Plans, Goals, and Understanding, Lawrence Erlbaum Associates, Hillsdale, NJ, 1977. This book is my cognitive science bible. I return to it over and over again for the insights it provides. Other reading will be from selected chapters and journal articles. I will put three copies of each outside my office (215 College of Computing Building) for students to borrow and copy for themselves and return. Most of the articles will also be on web reserve at the library.
Much of the work you will do on assignments will be in the context of commenting on and bringing together ideas we discuss in class. Rather than simply asking you all to write to me, I ask that you write to the class. For this, I provide a Co-Web, or SWIKI, http://xenex.cc.gatech.edu:8080/cip, a collaborative web site that allows you to submit your thoughts and comment on the thoughts of others. I’ll seed it with issues and questions; feel free to add your own to the set. I will let you know what requirements will be for participating in these on-line discussions.
Feel free to come by and talk to me any time. My main office is in the GCATT Building, and I am usually quite busy while I’m over there. However, I reserve many hours on Tuesdays and Thursdays in the College of Computing Building.
Office hours: Tuesday, 1:00 to 2:00, 4:30 to 5:00 ; Thursday, 12:00 to 3:00, 4:30 to 5:00 .
Office: College of Computing Room 215 (only during the listed hours).
Phone: 404-894-3285
Email: jlk@cc.gatech.edu
Tue Mar 30 INTRODUCTION
The CD approach to understanding cognition and cognitive systems; what we’re doing and where we’re going in this course; introduction to representation and inference.
Thurs Apr 1 Conceptual Dependency — Guest teacher: Kurt Eiselt
Required reading:
Schank, R.C., & Abelson, R. (1977). Scripts, Plans, Goals and Understanding, chapters 1 and 2, Lawrence Erlbaum Associates.
Schank, R.C. (1972). Conceptual Dependency: A Theory Of Natural Language Understanding. In Schank & Colby (eds.), Computer Models of Thought and Language, pp. 152-186.).
Tues Apr 6 Conceptual Dependency — putting it to work
Conceptual Dependency homework to be turned in and discussed. Bring a copy to turn in and one to mark up for yourself.
Required reading:
Lehnert, W. G. (1988) Knowledge-Based Natural Language Understanding. In H. Schrobe (Ed.), Exploring Artificial Intelligence, Morgan Kaufmann, San Mateo, CA.
Thurs Apr 8 Understanding I — Conceptual Analysis — Guest teacher: Kurt Eiselt
Required reading:
Birnbaum, L., & Selfridge, M. (1981), Conceptual Analysis of Natural Language. In Schank & Riesbeck (eds.), Inside Computer Understanding: Five Programs Plus Miniatures, pages 318-353, chapter 13, Lawrence Erlbaum.
Optional reading:
P. van den Broek (1990). The Causal Inference Maker: Towards a Process Model of Inference Generation in Text Comprehension. In D.A. Balota, G.B. Flores d'Arcais, & K. Rayner (eds.), Comprehension Processes in Reading, chapter 20, pages 423-445, Lawrence Erlbaum Associates, Hillsdale, NJ.
Tues Apr 13 Inference, Scripts, and Script Application
causal chains, managing chains of inference, the need to organize knowledge better for inference; a way to organize knowledge about the sequences of common, everyday activities: scripts
Required reading:
Schank and Abelson, chap 3.
Cullingford, R. (1981). SAM. In Schank & Riesbeck, editors, Inside Computer Understanding: Five Programs with Miniatures, Lawrence Erlbaum.
Optional:
DeJong, G (???). An Overview of the FRUMP System. In Strategies for Natural Language Processing.
Thurs Apr 15 Representation I
Required - read one of these in depth; make sure you understand what it is saying about creating representations
Domeshek, E.A. (1994). Do the Right Thing: A Component Theory for Indexing Stories as Social Advice, Chapters 1-4, Ph.D. thesis, Yale University, New Haven CT.
OR
Schank, R. C. & Carbonell, J. C. (1978?). Re: The Ghettysburg Address: Representing Social and Political Acts. Yale University. Dept. of Computer Science, Research Report #127.
Tues Apr 20 Representation II -- Plans and Goals
Required:
Schank and Abelson, Chaps. 4, 5, and 6
Wilensky, R. (1981). PAM. In Schank & Riesbeck, editors, Inside Computer Understanding: Five Programs with Miniatures, Lawrence Erlbaum.
Thurs Apr 22 Representation III — structure of representations
Required:
Barsalou, L.W. (1992). Frames, Concepts, and Conceptual Fields. In A. Lehrer & E.F. Kittay (eds.), Frames, Fields, and Contrasts: New Essays in Semantic and Lexical Organization, chapter 1, pages 21-72, Lawrence Erlbaum Associates, Hillsdale, NJ.
Tues Apr 27 Organizing and accessing knowledge structures
Required:
Schank, R.C. (1982). Failure-Driven Memory: Chapter 3 of Dynamic Memory, pages 37-61, Cambridge University Press.
Kolodner, J.L. (1983). Maintaining Organization in a Dynamic Long-Term Memory. Cognitive Science, 7:243-280.
Thurs Apr 29 Organizing and accessing knowledge structures (continued)
Required:
Kolodner, J.L. (1983). Reconstructive Memory: A Computer Model. Cognitive Science, 7:281-328.
Wharton, C.M., & Lange, T.E. (1994). Analogical Transfer Through Comprehension and Priming. Proceedings of CogSci-94.
Tues May 4 Understanding II — Integrated Processing I
Required:
Lebowitz, M. (1983). Memory-Based Parsing. Artificial Intelligence, 21:363-404.
Birnbaum, L. (1986). Integrated Processing in Planning and Understanding, chapters 1 and 10, Ph.D. Thesis, Research Report #489, Yale University, New Haven, CT.
Thurs May 6 Understanding III — Integrated Processing II
Required:
W. Lehnert, M.G. Dyer, P.N. Johnson, C.J. Yang & S. Harley, BORIS --- An Experiment in In-Depth Understanding of Narratives. Artificial Intelligence, 20, pp. 15-62, 1983.
Tues May 11 Understanding IV — Integrated Processing III
Required:
Ram, A. (1991). A Theory of Questions and Question Asking. The Journal of the Learning Sciences, 1(3&4):273--318.
Moorman, K., & Ram, A. (1994). Integrating Creativity and Reading: A Functional Approach. Proceedings of CogSci-94.
Carpenter, T., & Alterman, R. (1994). A Taxonomy for Planned Reading. Proceedings of CogSci-94.
Thurs May 13 Explanation
Required:
Ram, A. (1994). AQUA: Questions that Drive the Explanation Process. In R.C. Schank, A. Kass, & C.K. Riesbeck, editors, Inside Case-Based Explanation, chapter 7, Lawrence Erlbaum.
Schank, R.C., Kass, A., & Riesbeck, C.K. (1994). Micro-SWALE. Chapter 10 of Inside Case-Based Explanation, Lawrence Erlbaum.
Tues May 18 Using our Understanding II — Planning and Problem Solving
Required:
Hayes-Roth & Hayes-Roth (1979), A Cognitive Model of Planning. Cognitive Science, 3, pp. 275-310.
McDermott, D. (1978). Planning and Acting. Cognitive Science, 2.
Optional:
Hayes-Roth, B. (1995). An architecture for adaptive intelligent agents. Artificial Intelligence, 72:329-365.
Thurs May 20 Case-Based Reasoning
Required:
Kolodner, J.L. (1993 Case-Based Reasoning, ch 1 and 2, Morgan Kaufmann Publishers, San Mateo, CA.
Hammond, K. (1989). Case-Based Planning: Viewing Planning as a Memory Task, chapters 1-3, Academic Press.
Tues May 25 Analogical Reasoning
Required (tentative):
Cummins, D.D. (1994). Analogical Reasoning.
Falkenhainer, B. (1990). A Unified Approach to Explanation and Theory Formation. In Shrager & Langley, editors, Computational Models of Scientific Discovery and Theory Formation, Morgan Kaufmann.
Thurs May 27 Learning I — Inductive Learning
Required:
Porter, B.W., Bareiss, R., & Holte, R.C. (1990). Concept Learning and Heuristic Classification in Weak-Theory Domains. Artificial Intelligence, 45(1-2):229-263.
Lebowitz, M. (1986). UNIMEM. In R.S. Michalski, J.G. Carbonell, & T.M. Mitchell (eds.), Machine Learning II: An Artificial Intelligence Approach, Morgan Kaufmann Publishers, San Mateo, CA.
Optional:
Barsalou, L.W. (1991). Deriving Categories to Achieve Goals. In G.H. Bower (ed.), The Psychology of Learning and Motivation: Advances in Research and Theory, Volume 27, Academic Press.
Tues June 1 Learning II — Analytical Learning — An Explanation-Based Approach
Required:
Schank, R.C., Collins, G., & Hunter, L. (1986). Transcending Inductive Category Formation. Behavioral and Brain Sciences, 9(4).
DeJong, G., & Mooney, R. (1986). Explanation-Based Learning: An Alternative View. Machine Learning, 1:145-176.
Optional:
Mitchell, T.M., Keller, R., & Kedar-Cabelli, S. (1986). Explanation-Based Generalization: A Unifying View. Machine Learning, 1(1):47--80.
Wisniewski, E.J., & Medin, D.L. (1991). Harpoons and Long Sticks: The Interaction of Theory and Similarity in Rule Induction. In D. Fisher & M.J. Pazzani (eds.), Concept Formation: Knowledge and Experience in Unsupervised Learning, Morgan Kaufmann Publishers, San Mateo, CA.
OR
Wisniewski, E.J., & Medin, D.L. (1994). On the Interaction of Theory and Data in Concept Learning. Cognitive Science, 18(2):221-281.
Thurs June 3 — Pulling it all together
Required reading:
Kolodner, Case-Based Reasoning, ch 4.
Ram, A. & Leake, D.B. (in press). Learning, Goals, and Learning Goals. Chapter 1 of A. Ram & D.B. Leake, Goal-Driven Learning, MIT Press/Bradford Books, Cambridge, MA.