The paper describes a new conversation management approach which may apply to a class of mixed initiative information seeking applications. It employs an application-independent conversation model inspired by the conversation theory of Grosz and Sidner [1]. Based on the model, we design a multi-layer conversation manager which employs instance-based learning (IBL) to determine conversation plans, while performs modularized realization of each conversation move in a conversation plan. Because we adopt IBL to determine conversation plans, new conversation behaviors are easy to incorporate. Our realization of conversation moves is also application-independent. We illustrate this method with a real estate application.
By: Shimei Pan
Published in: RC23197 in 2004
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .