In this paper we explore a new theory of discourse structure that stresses the role of purpose and processing in discourse. In this theory, discourse structure is composed of three separate but interre-lated components: the structure of the sequence of utterances (called the linguistic structure), a struc-ture of purposes (called the intentional structure), and the state of focus of attention (called the attentional state). The linguistic structure consists of segments of the discourse into which the utter-ances naturally aggregate. The intentional structure captures the discourse-relevant purposes, expressed in each of the linguistic segments as well as relationships among them. The attentional state is an abstraction of the focus of attention of the participants as the discourse unfolds. The attentional state, being dynamic, records the objects, properties, and relations that are salient at each point of the discourse. The distinction among these components is essential to provide an adequate explanation of such discourse phenomena as cue phrases, referring expressions, and interruptions. The theory of attention, intention, and aggregation of utterances is illustrated in the paper with a number of example discourses. Various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored. This theory provides a framework for describing the processing of utterances in a discourse. Discourse processing requires recognizing how the utterances of the discourse aggregate into segments, recognizing the intentions expressed in the discourse and the relationships among intentions, and track-ing the discourse through the operation of the mechanisms associated with attentional state. This processing description specifies in these recognition tasks the role of information from the discourse and from the participants ' knowledge of the domain. 1

Introduction Cooperative Distributed Problem-Solving (CDPS) studies how a loosely-coupled network of problem solvers can work together to solve problems that are beyond their individual capabilities. Each problem-solving node in the network is capable of sophisticated problem solving and can work independently, but the problems faced by the nodes cannot be completed without cooperation. Cooperation is necessary because no single node has sufficient expertise, resources, and information to solve a problem, and different nodes might have expertise for solving different parts of the problem. For example, if the problem is to design a house, one node might have expertise on the strength of structural materials, another on the space requirements for different types of rooms, another on plumbing, another on electrical wiring, and so on. Different nodes might have different resources: some might be very fast at computation, others might have connections that speed communication, whil

This chapter surveys the field of user modeling in artificial intelligence dialog systems. First, reasons why user modeling has become so important in the last few years are pointed out, and definitions are proposed for the terms 'user model ' and 'user modeling component'. Research within and outside of artificial intelligence which is related to user modeling in dialog systems is discussed. In Section 2, techniques for constructing user models in the course of a dialog are presented and, in Section 3, recent proposals for representing a wide range of assumptions about a user's beliefs and goals in a system's knowledge base are surveyed. Examples for the application of user models in systems developed to date are then given, and some social implications discussed. Finally, unsolved problems like coping with collective beliefs or resource-limited processes are investigated, and prospects for applicationoriented research are outlined. Although the survey is restricted to user models in naturallanguage dialog systems, most of the concepts and methods discussed can be extended to AI dialog systems in general.

Abstract not found

This paper introduces Linguistic Style Improvisation, a theory and set of algorithms for improvisation of spoken utterances by artificial agents, with apphcations to interactive story and dialogue systems. We argue that hnguistic style is a key aspect of character, and show how speech act representations common in AI can provide abstract representations from which computer characters can improvise. We show that the mechanisms proposed introduce the possibility of socially oriented agents, meet the requirements that lifehke characters be behevable, and satisfy particular criteria for improvisation proposed by Hayes-Roth.

This paper describes a novel method by which a spoken dialogue system can learn to choose an optimal dialogue strategy from its experience interacting with human users. The method is

this paper, we present a plan-based model for response generation during collaborative planning, based on a recursive Propose-Evaluate-Modify framework for modeling collaboration. We focus on identifying strategies for content selection when 1) the system initiates information-sharing to gather further information in order to make an informed decision about whether to accept a proposal from the user, and 2) the system initiates collaborative negotiation to negotiate with the user to resolve a detected conflict in the user's proposal. When our model determines that information-sharing should be pursued, it selects a focus of information-sharing from among multiple uncertainties that might be addressed, chooses an appropriate information-sharing strategy, and formulates a response that initiates an information-sharing subdialogue. When our model determines that conflicts must be resolved, it selects the most effective conflicts to address in resolving disagreemen t about the user's proposal, iden tiffes appropriate jus tiffcation for the sys tem' s claims, and formulates a response that initiates a negotiation subdialogue

This paper presents empirical results comparing spoken and keyboard communication. It is shown that speakers attempt to achieve more detailed goals in giving instructions than do users of keyboards. One specific kind of fine-grained communicative act, a request that the hearer identify the referent of a noun phrase, is shown to dominate spoken instruction-giving discourse, but is nearly absent from keyboard discourse. Most important, these requests are only achieved "indirectly". - through utterances whose surface forms do not explicitly convey the speakers' intent. A plan-based theory of communication is shown to uncover the speakers' intentions underlying many cases of indirect identification requests found in the corpus, once an action for referent identification has been posited. In so doing, the theory demonstrates how intent (or plan) recognition can be applied in reasoning about the use of a description. As a consequence of this approach, it is shown that the conditions on the planning of successful identification requests account for Searle's conditions on the act of referring. It is concluded that intent recognition will need to be a central focus for pragmatics/discourse components of future speech understanding systems, and that computational linguistics needs to develop formalisms for reasoning about speakers' use of descriptions

This paper presents a plan-based model that handles negotiation subdialogues by inferring both the communicative actions that people pursue when speaking and the beliefs underlying these actions. We contend that recognizing the complex dis- course actions pursued in negotiation subdialogues (e.g., expressing doubt) requires both a multi- strength belief model and a process model that combines different knowledge sources in a unified framework. We show how our model identifies the structure of negotiation subdialogues, including recognizing expressions of doubt, implicit acceptance of communicated propositions, and negotiation subdialogues embedded within other negotiation subdialogues.

Negotiation is an important part of task-oriented expert-consultation dialogues. This paper presents a plan-based model for understanding cooperative negotiation subdialogues. Our sys-tem infers both the communicative actions that people pursue when speaking and the beliefs underlying these actions. Beliefs, and the strength of these beliefs, are recognized from the surface form of utterances,from discourse acts, and from the explicit and implicit acceptance of previous utterances. Our algorithm for recognizing discourse actions combines linguistic, world, and con-textual knowledge in a unified framework. By combining these different knowledge sources, we are able to recognize complex discourse acts such as expressing doubt, to identify the relationship of utterances to one another, and to model negotiation subdialogues. Since negotiation is an inte-gral part of multiagent activity, our process model addresses an important aspect of cooperative interaction and thus is a step toward an intelligent and robust natural language consultation system.