Natural Language in Computer-Human Interaction

a CHI 99 Special Interest Group: 9:00 am - 10:30 am, May 20, 1999 (tentative day/time)
            Nancy Green                 David G. Novick
     Carnegie Mellon University             EURISCO


With the growing interest in systems that use natural-language processing (NLP) as part of a human-computer interface, researchers and practitioners who work with these interfaces are finding that two general fields of research, CHI and NLP, are complementary and converging. In the NLP research community, there is increasing interest in use of natural language, both spoken and written, in intelligent multimodal and multimedia interfaces, e.g.,

And in the CHI research community, there are investigations on a number of related issues such as usability of on-line documentation (e.g., Landauer et al., 1993; Brockmann, 1986), hypertext (e.g., Chen & Rada, 1996), spoken-dialogue systems as interfaces (e.g., Yankelovich, Levow, & Marx, 1995; Hansen, Novick & Sutton, 1996; Walker et al., 1998), and language/audio resources (e.g., Arons, 1993).

Although there are several annual conferences that provide an opportunity for the two communities to interact, such as the yearly International Conference on Intelligent User Interfaces (IUI) and the Annual ACM Symposium on User Interface Software and Technology (UIST), the time is right for interaction at their respective primary meetings, the annual conference of the Association for Computational Linguistics (ACL) and the annual CHI conference.

Some of the technical issues of interest to both communities are

  1. For what and under what conditions is NL appropriate in the human-computer interface?
  2. What are the unique technical requirements for NLP in the human-machine interface? (e.g., coordination of generated text and graphics, incremental generation and interpretation, robust interpretation, modeling turn-taking and initiative in dialogue)


The primary goal of this SIG is to provide an opportunity for CHI attendees from both the CHI and NLP research communities who are interested in use of NL in the computer interface to discuss issues of mutual interest. The participants could discuss:


The SIG's format will consist of a 90 minute discussion moderated by the organizers. The session will begin with a 15-minute period during which participants will select issues to discuss, will continue with an hour of discussion of the top several issues, and end with a 15-minute wrap-up in which participants can discuss possible follow-up activities.

Our rationale for this activity plan is that we want to keep the agenda flexible because the point of the SIG is precisely to identify issues, commonalities and differences; an over-specific prepackaged agenda would risk curtailing valuable exploration of these questions. Complementary to this need to be flexible, though, we have proposed an overall schedule that should enable the participants to identify key issues, agree on which to discuss, hold substantive discussions on these top issues, and have time to organize follow-up actions.

SIG Activity Plan

The SIG's format will consist of a 90-minute discussion moderated by the organizers. The session will begin with a 15-minute period during which participants will select issues to discuss, will continue with an hour of discussion of the top several issues, and end with a 15-minute wrap-up in which participants can discuss possible follow-up activities.

Who Should Attend

We invite all members of the CHI and NLP communities who are interested in use of natural language in the human-computer interface.


To attend the SIG meeting, you must register for the main CHI99 conference. (The deadline for early conference registration is April 8.) For registration information see the CHI99 Web Page.


Nancy Green is a Systems Scientist at the Human-Computer Interaction Institute, Carnegie Mellon University. Her current research is in intelligent multimedia presentation systems on techniques for automatic generation of coordinated text and information graphics. A member of the Visualization and Intelligent Interfaces Group at CMU, she is also interested in the general question of the role of NL in new forms of human-computer interaction such as information visualization. Prior to that, as a Postdoctoral Fellow at CMU, her research was on use of a computational cognitive architecture for discourse processing. She earned a Ph. D. in Computer Science from the University of Delaware and a Master of Arts in Linguistics from the University of North Carolina at Chapel Hill.

David G. Novick is director of research at the European Institute of Cognitive Sciences and Engineering, in Toulouse, France. His research interests focus on interactive systems, including computational models of conversation, technologically mediated communication, and human-computer interaction. Applications of these interests include systems design and development methods, particularly in aviation and aerospace. He earned his J.D. from Harvard Law School in 1977 and his Ph.D. in Computer and Information Science from the University of Oregon in 1988. He is an active member of the bars of Oregon and District of Columbia. He was a founding member of the Computer-Human Interaction Forum of Oregon (CHIFOO) and of IHM-Toulouse. He co-organized the CHI 96 workshop on the CHI Ten-Year View: Creating and Sustaining Common Ground, and co-organized special interest groups at CHI 97 and CHI 98 that launched SIGCHI's task force and committee on international issues. He is the CHI liaison for SIGDIAL, the ACL's special interest group on dialogue and discourse.


Arons, B. (1993). Speech Skimmer: Interactively skimming recorded speech. Proceedings of UIST 93, 187-196.

Brockman, John R. Writing Better Computer User Documentation: from Paper to Online. John Wiley and Sons, Inc., New York, 1986.

Chen, C., and Rada, R. Interacting with Hypertext: A Meta-Analysis of Experimental Studies. Human-Computer Interaction, 1996, v. 11, 125-156.

Hansen, B., Novick, D., and Sutton, S. (1996). Systematic design of spoken prompts, Conference on Human Factors in Computing Systems (CHI'96), Vancouver, BC, April, 1996, 157-164.

Landauer, T., Egan, D., Remde, J., Lesk, M., Lochbaum, C., and Ketchum, D. Enhancing the Usability of Text through Computer Delivery and Formative Evaluation: the SuperBook Project, in McKnight, C., Dillon, A., and Richardson, J. (eds), Hypertext: A Psychological Perspective, New York, Ellis Horwood, 1993, 71-136.

Walker, M., Fromer, J., Di Frabbrizio, G., Mestel, C., and Hindle, D. (1998). What can I say?: Evaluating a spoken language interface to email, Human Factors in Computing Systems (CHI 98), Los Angeles, CA, April, 1998, 582-589.

Yankelovich, N., Levow, G., and Marx, M. Designing SpeechActs: Issues in speech user interfaces, Proceedings of Computer Human Interaction, 1995, 369-376.

This Site (USA):
Mirror site (France):
DGN, March 28, 1999