Collaborating with Focused and Unfocused Users under Imperfect Communication
- 682 Downloads
A totally focused user always finishes the current task or subtask before moving on to another. Typical users, however, sometimes shift back and forth between incomplete tasks and do not always communicate before doing so. This behavior poses a problem for a software agent that uses plan recognition to support its collaboration with users. Our solution is a discourse interpretation algorithm which balances between asking too many questions about a user’s intentions and sometimes being wrong about them.
Unable to display preview. Download preview PDF.
- 1.S. Carberry. Incorporating default inferences into plan recognition. In Proc. 8th Nat. Conf. AI, volume 1, pages 471–8, july 1990.Google Scholar
- 3.B. J. Grosz and C. L. Sidner. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3):175–204, 1986.Google Scholar
- 4.D. Gruen, C. Sidner, C. Boettner, and C. Rich. A collaborative assistant for email. In oc. ACM SIGCHI Conference on Humam Factors in Computing Systems, Pittsburgh, PA, May 199Google Scholar
- 5.N. Lesh, C. Rich, and Candance L. Sidner. Using plan recognition in human-computer collaboration. In Proc. of 7th Int. Conf. User Modelling, pages 23–32, 1999.Google Scholar
- 6.K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the Assoc. for Computational Linguistics, pages 33–38, Berkeley, CA, 1991.Google Scholar
- 7.K. E. Lochbaum. A collaborative planning model of intentional structure. Computational Linguistics, 24(4), December 1998.Google Scholar