Subset languages for conversing with collaborative interface agents

This paper reports on experiments with subjects who must learn to use a small artificially constructed subset language (of English) to interact with a conversational spoken language system. The subjects converse with a collaborative interface agent about tasks involving TV recording and schedule navigation. The subjects perform their tasks in two conditions, one with contextually appropriate help on what to say always available on the screen and those with only a help sheet that they request to see. Our experiments indicate that users can perform their tasks in either condition, but demonstrate limits in remembering the language in a subsequent session. Accepted for presentation at Intern’l Conf. on Spoken Language Systems, 2002 This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Copyright c ©Mitsubishi Electric Research Laboratories, Inc., 2002 201 Broadway, Cambridge, Massachusetts 02139 Submitted August 2002.