6.892 Computational Models of Discourse

Spring 2004

Cherokee alphabet.
Cherokee Alphabet. (Image courtesy of the Clinton White House Web site.)

Course Highlights

This course features a complete set of lecture notes. In addition an extensive bibliography of assigned and recommended readings is provided in the readings section.

Course Description

This course is a graduate level introduction to automatic discourse processing. The emphasis will be on methods and models that have applicability to natural language and speech processing.

The class will cover the following topics: discourse structure, models of coherence and cohesion, plan recognition algorithms, and text segmentation. We will study symbolic as well as machine learning methods for discourse analysis. We will also discuss the use of these methods in a variety of applications ranging from dialogue systems to automatic essay writing.

This subject qualifies as an Artificial Intelligence and Applications concentration subject.

Technical Requirements

Postscript viewer software, such as Ghostscript/Ghostview, can be used to view the .ps files found on this course site. File decompression software, such as Winzip® or StuffIt®, is required to open the .gz files found on this course site.

Donate Now

Staff

Instructor:
Prof. Regina Barzilay

Course Meeting Times

Lectures:
Two sessions / week
1.5 hours / session

Level

Graduate