论文信息 - User-tailored generation for spoken dialogue: an experiment

User-tailored generation for spoken dialogue: an experiment

Recent work on evaluation of spoken dialogue systems suggests that the information presentation phase of complex dialogues is often the primary contributor to dialogue duration. Therefore, better algorithms are needed for the presentation of complex information in speech. This paper evaluates the effect of a user model on generation for three dialogue strategies: SUMMARY, COMPARE and RECOMMEND. We present results showing that (a) both COMPARE and RECOMMEND strategies are effective; and (b) the user model is useful.

[1] R. L. Keeney,et al. Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[2] John B. Kidd,et al. Decisions with Multiple Objectives—Preferences and Value Tradeoffs , 1977 .

[3] Johanna D. Moore,et al. An Empirical Study of the Influence of User Tailoring on Evaluative Argument Effectiveness , 2001, IJCAI.

[4] Marilyn A. Walker,et al. SPoT: A Trainable Sentence Planner , 2001, NAACL.

[5] Marilyn A. Walker,et al. Quantitative and Qualitative Evaluation of Darpa Communicator Spoken Dialogue Systems , 2001, ACL.

[6] F. B. Vernadat,et al. Decisions with Multiple Objectives: Preferences and Value Tradeoffs , 1994 .

[7] Daniel Marcu,et al. Building Up Rhetorical Structure Trees , 1996, AAAI/IAAI, Vol. 2.

[8] Johanna D. Moore,et al. Speech-Plans: Generating Evaluative Responses in Spoken Dialogue , 2002, INLG.

[9] Johanna D. Moore,et al. A strategy for generating evaluative arguments , 2000, INLG.

[10] F. H. Barron,et al. SMARTS and SMARTER: Improved Simple Methods for Multiattribute Utility Measurement , 1994 .

[11] Michael Johnston,et al. MATCH: multimodal access to city help , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..