Slide Presentations on Other People's Work

The following are slide presentations (by me) on work by others, used for an internal discussion group on topics in AI. All of these papers are extremely interesting, some are among my favorite papers in Artificial Intelligence.

• Attempto Controlled English, by Norbert Fuchs - A machine-understandable controlled language.
  • Discussion slides (by Peter Clark)
  • Source paper: N. E. Fuchs, U. Schwertel, R. Schwitter, Attempto Controlled English - Not Just Another Logic Specification Language; in P. Flener (ed.): Logic-Based Program Synthesis and Transformation, Eighth International Workshop LOPSTR'98, Manchester, UK, June 1998. Lecture Notes in Computer Science 1559, Springer Verlag, 1999.
  • Other material: The Attempto Web Site
• An Enquiry into Computer Understanding, by Peter Cheeseman - A discussion of the merits of probabilistic reasoning.
  • Discussion slides (by Peter Clark)
  • Source paper: P. Cheeseman, "An Enquiry into Computer Understanding", in Computational Intelligence 4 (1) pp58-66 (1988).
• The Naive Physics Perplex, by Ernest Davis - A cry of dispair that logic-based AI will never scale beyond microworlds.
  • Discussion slides (by Peter Clark)
  • Source paper: E. Davis, "The Naive Physics Perplex", AI Magazine 19 (4), Winter 1998, pp51-79.
• Processing Metonymy and Metaphor, by Dan Fass - A discussion of these phenomena by an expert in the field.
  • Discussion slides (by Peter Clark)
  • Source paper: D. Fass, "met*: a method for discriminating metonymy and metaphor by computer", Computational Linguistics 17 (1), March 1991, pp 49-90.
  • Other material: Processing Metonymy and Metaphor (book), by Dan Fass, Ablex Publishing, UK, 1997.
• Extracting Knowledge-Bases from Machine-Readable Dictionaries: Have We Wasted Our Time?, by Nancy Ide and Jean Veronis - Questioning the value of this once-popular goal in the NLP community.
  • Discussion slides (by Peter Clark)
  • Source paper: N. Ide, J. Veronis. Extracting Knowledge-Bases from Machine-Readable Dictionaries: Have We Wasted Our Time?, Proc KB&KB'93 Workshop, 1993, pp257-266.
• I don't believe in Word Senses, by A. Kilgarriff - A critique of the problems in the notion of "word senses" in NLP
  • Discussion slides (by Peter Clark)
  • Source paper: A. Kilgarriff. "I don't believe in Word Senses", in Computers and the Humanities, 31 (2), pp 91-113, 1997.
• Discovery of Inference Rules for Question Answering, by Dekang Lin and Patrick Pantel - Interesting work in extracting world knowledge by trawling through tons of text.
  • Discussion slides (by Peter Clark) from 2003 discussion group meeting
  • Discussion slides (by Peter Clark) from 2007 discussion group meeting
  • Source paper: D. Lin, P. Pantel. "Discovery of Inference Rules for Question Answering", in Natural Language Engineering 7(4):343-360, 2001.
• A Critique of Pure Reason, by John McDermott - A lament about the failure of deductive logic to model "real" intelligent reasoning (followed by rebuttals from others)
  • Discussion slides (by Peter Clark)
  • Source paper: McDermott, D. 1987. A critique of pure reason. Computational Intelligence, 3, pp. 151-160, with commentaries pp 161-237.
• A Framework for Representing Knowledge, by Marvin Minsky - Some highly influential ideas on the structure and organization of knowledge for intelligence
  • Discussion slides (by Peter Clark) - rather weak, just 3 short overview slides
  • Source paper: M. Minsky. "A Framework for Representing Knowledge". Reprinted in: Readings in Knowledge Representation, 1985, pp 245-262, CA:Kaufmann.
• Semantics of Paragraphs, by Wlodek Zadrozny and Karen Jensen - An elaborate (and largely unimplemented) theory of knowledge-based, paragraph-level natural language processing.
  • Discussion slides (by Peter Clark)
  • Source paper: W. Zadrozny, K. Jensen, "Semantics of Paragraphs", in Computational Linguistics 17 (2) pp171-209 (1991).
• TextNet: A Text-Based Intelligent System, by Sanda Harabagiu and Dan Moldovan - an attempt to leverage WordNet for text understanding
  • Discussion slides (by Peter Clark)
  • Source paper: S. Harabagiu, D. Moldovan. "TextNet --- a text-based intelligent system." In: Journal for Natural Language Engineering, vol 3, 1997, Cambridge University Press, pages 171-190.
• Beating Common Sense into Interactive Applications, by Henry Lieberman, Hugo Liu, Push Singh, Barbara Barry - a list of ideas on applications for a common-sense knowledge base, most backed by student-created prototypes
  • Discussion slides (by Peter Clark)
  • Source paper: Henry Lieberman, Hugo Liu, Push Singh, Barbara Barry. Beating Common Sense into Interactive Applications. In AI Magazine, Winter 2004, pp63-76.