A Computational Mechanism for Initiative in Answer Generation

  • Authors:

  • Nancy Green;Sandra Carberry

  • Affiliations:

  • School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213/ e-mail: Nancy.Green@cs.cmu.edu;Dept. of Computer Science, University of Delaware, Newark, Delaware 19716/ e-mail: carberry@cis.udel.edu

  • Venue:
  • User Modeling and User-Adapted Interaction
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

Initiative in dialogue can be regarded as the speaker taking the opportunity to contribute more information than was his obligation in a particular discourse turn. This paper describes the use of stimulus conditions as a computational mechanism for taking the initiative to provide unrequested information in responses to Yes–No questions, as part of a system for generating answers to Yes–No questions. Stimulus conditions represent types of discourse contexts in which a speaker is motivated to add unrequested information to his answer. Stimulus conditions may be triggered not only by the discourse context at the time when the question was asked, but also by the anticipated context resulting from providing part of the response. We define a set of stimulus conditions based upon previous linguistic studies and a corpus analysis, and describe how evaluation of these stimulus conditions makes use of information from a User Model. Also, we show how the stimulus conditions are used by the generation component of the system. An evaluation was conducted of the implemented system. The results indicate that the responses generated by our system containing extra information provided on the basis of this initiative mechanism are viewed more favorably by users than responses without the extra information.