Special topics in media technology: computational semantics

Lectures: 1 session / week, 2 hours / session

How do words get their meanings? How can word meanings be represented and used by machines? We will explore three families of approaches to these questions from a computational perspective. Relational / structural methods such as semantic networks represent the meaning of words in terms of their relations to other words. Knowledge of the world through perception and action leads to the notion of external grounding, a process by which word meanings are 'attached' to the world. How an agent theorizes about, and conceptualizes its world provides yet another foundation for word meanings. We will examine each of these perspectives, and consider ways to integrate them.

Reading 1.1: Harnad, S. "The Symbol Grounding Problem." Physica D 42 (1990): 335-346

Reading 1.2: Quillian, M. "Semantic Memory." Semantic Information Processing. Edited by M. Minsky. Cambridge, M. A.: MIT Press, 1968, pp. 216-270.

Reading 2.1: Miller, G. "Nouns in WordNet." WordNet: An Electronic Lexical Database. Edited by C. Fellbaum. MIT Press, 1998.

Reading 2.2: Pustejovsky, J. "Type construction and the logic of concepts." The language of word meaning. Edited by P. Bouillon, and F. Busa. Cambridge University Press, 2001.

The following readings will be discussed in class during sess #7:

Reading 3.1: Brooks, R. A. "Intelligence Without Representation." Artificial Intelligence Journal 47 (1991): 139–159.

Reading 3.2: Smith, Brian Cantwell. On the origin of objects. MIT Press. excerpts.

Reading 4.1: Gardenfors, P. "Symbolic, conceptual and subconceptual representations." Human and Machine Perception: Information Fusion. Edited by V. Cantoni, V. di Gesù, A. Setti, and D. Tegolo. N. Y.:Plenum Press, 1997, pp. 255-270.

Reading 4.2: Regier, T., and Carlson, L. "Grounding spatial language in perception: An empirical and computational investigation." Journal of Experimental Psychology: General, 130(2) (2001): 273-298.

Reading 4.3: Hofstadter, D. "A Review of Mental Leaps: Analogy in Creative Thought." AI Magazine (Fall 1995) 75-80.

Reading 5.1: Goldstone, R. L., and Rogosky, B. J. "Using relations within conceptual systems to translate across conceptual systems." Cognition 84, 295-320.

Summaries of papers only; to be discussed during sess #12.

Reading 6.1: Allen, James. Chapter 13 in Natural language understanding. Benjamin/Cummings, 1995.

Reading 6.2: Meuller, Erik T. ThoughtTreasure: A natural language/commonsense platform. 2002.

Summaries / critiques due by noon, a day before sess #11; to be discussed during sess #11.

Reading 7.1: Gopnik, A. "The Scientist as Child." Philosophy of Science 63(4) (1996): 485-514.

Reading 7.2: Carey, S., and Spelke, E. "Science and core knowledge." Philosophy of science 63(4) (1996): 515-533.

Summaries / critiques due by 10am, sess #12; to be discussed during sess #12

Reading 8.1: Jackendoff, R. Chapter 9 in Foundations of Language. Oxford University Press, 2002.

Reading 8.2: Jackendoff, R. Chapters 10a, 10b in Foundations of Language. Oxford University Press, 2002.

Don't show me this again

This is one of over 2,200 courses on OCW. Find materials for this course in the pages linked along the left.

MIT OpenCourseWare is a free & open publication of material from thousands of MIT courses, covering the entire MIT curriculum.

No enrollment or registration. Freely browse and use OCW materials at your own pace. There's no signup, and no start or end dates.

Knowledge is your reward. Use OCW to guide your own life-long learning, or to teach others. We don't offer credit or certification for using OCW.

Made for sharing. Download files for later. Send to friends and colleagues. Modify, remix, and reuse (just remember to cite OCW as the source.)

Learn more at Get Started with MIT OpenCourseWare