Connict Resolution in Collaborative Discourse 1. Motivation

Curry I. Guinn Alan W. Biermann Department of Computer Science Duke University Durham, North Carolina 27706 ABSTRACT This paper presents a model of collaborative discourse which integrates problem-solving, discourse, and con ict resolution. Experimental evidence obtained from an implementation of this theory demonstrates the e ectiveness of the con ict resolution methods within the model. 1. Motivation Two recently implemented voice dialogue systems utilize the principle that discourse is a by-product of cooperative problem-solving[1, 2]. The computer participant in both of these systems proceeds by attempting to prove or solve some goal, and when the system is blocked, it has the option of using dialogue to obtain the necessary information in order to continue its proof. This dialogue mechanism has been described as the missing axiom theory of discourse[3]. This paper extends this theory to develop a uni ed model of collaborative discourse within the missing axiom framework which includes several mechanisms for con ict resolution: 1) the varying of dialogue initiative between participants, 2) the generation of negotiation utterances when con icts occur, and 3) the utilization of summarizing statements to assist in coordinating goal planning. Furthermore, this paper presents experimental data obtained through an implementation of this model which demonstrates an increase in e ciency due to these resolution methods. 2. The Collaborative Model The model developed assumes two beings are working collaboratively to solve a problem each using its own private knowledge and user model of the other participant as illustrated in Figure 1. A set of facts about the problem is distributed in some manner between the participants, and the discourse involves the interactions needed to prove the subgoals required to solve the global problem. The process involves each participant attempting to solve the problem alone and making occasional requests of the other when particular subgoals fail. When a participant receives a request from the other, it has the option of trying to solve the requested goal and passing it back, or ignoring the request and pursuing its own goal. Plan ? Plan Dialogue Knowledge Base User Model Knowledge Base User Model Participant B Participant A