generation. It shows what can be done in a fairly complete system that understands natural language (typed or spoken), answers questions and performs various actions, and responds in natural language (typed and spoken).
Problems that arose in the design of HWIM were precursors of those that are central issues in AI research today. For example, the speech-act issues for HWIM are similar to those studied by Cohen ( 1978), Cohen and Perrault ( 1979), and Allen ( 1979). Questions of knowledge representation closely related to those faced in HWIM have been pursued by Bobrow and Winograd ( 1977), Brachman ( 1979), and Fahlman ( 1979). (Also see Brachman & Smith, 1980). Language generation in a discourse context similar to HWIM's has been studied by McDonald ( 1980) and others. Finally, the issue of interactions among syntax, semantics, and pragmatics is crucial in the work of Schank and Abelson ( 1977), Bobrow ( 1978), Woods ( 1980), and others.
The characteristics of HWIM reflect the goal of natural communication between a person and a computer assistant. Even in its limited domain, it illustrates the extent to which natural communication depends on diverse kinds of knowledge in both communicants. The structure of HWIM can provide a useful framework for obtaining a better understanding of natural communication.
HWIM was developed over a 5-year period as the BBN speech -understanding system. This chapter, which draws from Volume 5 of the final report on HWIM ( Woods et al., 1976), focuses on the component of the system embodying semantic and pragmatic knowledge. Many people worked on the system; those specifically involved with the parts of the system discussed here included Bonnie Webber, Bill Woods, Laura Gould, Greg Harris, Craig Cook, Lyn Bates, Geff Brown, and David Grabel. For discussions of other speech understanding systems, see Erman et al. ( 1980), Lea ( 1980), and Walker ( 1978).
Bill Woods, Bonnie Webber, Scott Fertig, Andee Rubin, Ron Brachman, Marilyn Adams, Phil Cohen, Allan Collins, and Marty Ringle contributed useful suggestions and criticisms to this chapter. Cindy Hunt helped in the preparation. The system development and much of the writing was supported by the Advanced Research Projects Agency of the Department of Defense and was monitored by ONR under Contract No. N00014-75-C 0533. Additional work on the chapter itself was supported by the National Institute of Education under Contract No. US-NIE-C-400-76-0116. Views and conclusions contained here are those of the author and should not be interpreted as representing the official opinion or policy of DARPA, NIE, the U.S. Government, or any other person or agency connected with them.
Allen J. A plan-based approach to speech act recognition (Tech. Rep. No. 131/79). Toronto: Department of Computer Science, University of Toronto, 1979.