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

this paper was supported by a gift from the Systems Development Foundation. The research was done as part of my doctoral thesis [19], which was supported by a gift from the Systems Development Foundation, by an IBM Graduate Fellowship, by the Defense Advanced Research Projects Agency under Contract N00039-84-K-0078 and by the Office of Naval Research under Contract N00014-855-C-0013. My sincere thanks to Barbara Grosz, and to all the others, too numerous to list here, who contributed to my thesis effort.

... this paper, we argue that, to handle explanation dialogues successfully, a discourse model must include information about the intended effect of individual parts of the text on the hearer, as well as how the parts relate to one another rhetorically. We present a text planner that records this information and show how the resulting structure is used to respond appropriately to a follow-up question.

An agent's ability to understand an utterance depends upon its ability to relate that utterance to the preceding discourse. The agent must determine whether the utterance begins a new segment of the discourse, completes the current segment, or contributes to it. The intentional structure of the discourse, comprised of discourse segment purposes and their interrelationships, plays a central role in this process (Grosz and Sidner, 1986). In this thesis, we provide a computational model for recognizing intentional structure and utilizing it in discourse processing. The model specifies how an agent's beliefs about the intentions underlying a discourse affects and are affected by its subsequent discourse. We characterize this process for both interpretation and generation and then provide specific algorithms for modeling the interpretation process. The collaborative planning framework of SharedPlans (Lochbaum, Grosz, and Sidner, 1990; Grosz and Kraus, 1993) provides the basis for our model ...

Cue phrases are linguistic expressions such as now and well that function as explicit indicators of the structure of a discourse. For example, now may signal the beginning of a subtopic or a return to a previous topic, while well may mark subsequent material as a response to prior material, or as an explanatory comment. However, while cue phrases may convey discourse structure, each also has one or more alternate uses. While incidentally may be used sententially as an adverbial, for example, the discourse use initiates a digression. Although distinguishing discourse and sentential uses of cue phrases is critical to the interpretation and generation of discourse, the question of how speakers and hearers accomplish this disambiguation is rarely addressed. This paper reports results of empirical studies on discourse and sentential uses of cue phrases, in which both text-based and prosodic features were examined for disambiguating power. Based on these studies, it is proposed that discourse versus sentential usage may be distinguished by intonational features, specifically, pitch accent and prosodic phrasing. A prosodic model that characterizes these distinctions is identified. This model is associated with features identifiable from text analysis, including orthography and part of speech, to permit the application of the results of the prosodic analysis to the generation of appropriate intonational features for discourse and sentential uses of cue phrases in synthetic speech. 1.

Abstract not found

Existing models of plan inference (PI) in conversation have assumed that the agent whose plan is being inferred (the actor) and the agent drawing the inference (the observer) have identical beliefs about actions in the domain. I argue that this assumption often results in failure of both the PI process and the communicative process that PI is meant to support. In particular, it precludes the principled generation of appropriate responses to queries that arise from invalid plans. I describe a model of PI that abandons this assumption. It rests on an analysis of plans as mental phenomena. Judgements that a plan is invalid are associated with particular discrepancies between the beliefs that the observer ascribes to the actor when the former believes that the latter has some plan, and the beliefs that the observer herself holds. I show that the content of an appropriate response to a query is affected by the types of any such discrepancies of belief judged to be present in the plan inferred to underlie that query. The PI model described here has been implemented in SPIRIT, a small demonstration system that answers questions about the domain of computer mail.

This paper presents a computational model of how conversational participants collaborate in making referring expressions. The model is based on the planning paradigm. It employs plans for constructing and recognizing referring expressions and meta-plans for constructing and recognizing clarifications. This allows the model to account for the generation and understanding both of referring expressions and of their clarifications in a uniform framework using a single knowledge base.

Terminological systems, such as KL-ONE and K-Rep, are widely used in AI to represent and reason with concept descriptions. They compute subsumption relations between concepts and automatically classify concepts into a taxonomy. Each concept in the taxonomy describes a set of possible instances which are a superset of those described by its descendants. One limitation of current systems is their inability to handle complex compositions of concepts, such as constraint networks where each node is described by an associated concept. For example, plans are often represented (in part) as collections of actions related by a rich variety of temporal constraints. The T-REX system integrates terminological reasoning with constraint network reasoning to classify such plans, producing a "terminological" plan library. T-REX also introduces a new view of plan recognition as a process which dynamically partitions the plan library by modalities, e.g., necessary, possible and impo...

This paper presents an analysis of purpose clauses in the context of instruction understanding. Such analysis shows that goals affect the interpretation and / or execution of actions, lends support to the proposal of using generation and enablement to model relations between actions, and sheds light on some inference processes necessary to interpret purpose clauses.