Author(s)Rosenberg, Steven T.
An essential step in understanding connected discourse is the ability to link the meanings of successive sentences together. Given a growing database to which new sentence meanings must be linked, which out of many possible inference chains will succeed? To which items already in a data base is a new item relevent? To assure easy understandability of text the amount of processing time spent on unsuccessful linkage attempts must be reduced. This paper develops a preliminary theory of discourse structure. Several newspaper articles were examined in the light of this theory. Two examples were worked out in detail to explore how a hypothetical discourse understander might use the model of discourse structure to represent knowledge gained from processing text.
This report describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology. It was supported in part by the National Science Foundation under grant C40708X and in part by the Advanced Research Projects Agency of the Department of Defense under Office of Naval Research contract N00014-75-C-0643. The views and conclusions contained in this document are those of the author and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the National Science Foundation or the United States Government.
MIT Artificial Intelligence Laboratory
MIT Artificial Intelligence Laboratory Working Papers, WP-130;