For people to contribute to discourse, they must do more than utter the right sentence at the right time. The basic requirement is that they odd to their common ground in on orderly way. To do this, we argue, they try to establish for each utterance the mutual belief that the addressees hove understood what the speaker meant well enough for current purposes. This is accomplished by the collective actions of the current contributor and his or her partners, and these result in units of conversation called contributions. We present a model of contributions and show how it accounts for o variety of features of everyday conversations.

... 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 ...

The Trains project is an effort to build a conversationally proficient planning assistant. A key part of the project is the construction of the Trains system, which provides the research platform for a wide range of issues in natural language understanding, mixedinitiative planning systems, and representing and reasoning about time, actions and events. Four years have now passed since the beginning of the project. Each year we have produced a demonstration system that focused on a dialog that illustrates particular aspects of our research. The commitment to building complete integrated systems is a significant overhead on the research, but we feel it is essential to guarantee that the results constitute real progress in the field. This paper describes the goals of the project, and our experience with the effort so far. This paper is to appear in the Journal of Experimental and Theoretical AI, 1995. The TRAINS project has been funded in part by ONR/ARPA grant N00014-92-J-1512, U.S. Air ...

We have been examining mixed-initiative planning systems in the context of command and control or logistical overview situations. In such environments, the human and the computer must work together in a very tightly coupled way to solve problems that neither alone could manage. In this paper, we describe our implementation of a prototype version of such a system, TRAINS-95, which helps a manager solve routing problems in a simple transportation domain. Interestingly perhaps, traditional planning technology does not play a major role in the system, and in fact it is difficult to see how such components might fit into a mixed-initiative system. We describe some of these issues, and present our agenda for future research into mixed-initiative plan reasoning. At this writing, the TRAINS-95 system has been used by more than 100 people to solve simple problems at various conferences and workshops, and in our experiments.

This paper describes a system that leads us to believe in the feasibility of constructing natural spoken dialogue systems in task-oriented domains. It specifically addresses the issue of robust interpretation of speech in the presence of recognition errors. Robustness is achieved by a combination of statistical error post-correction, syntactically- and semantically-driven robust parsing, and extensive use of the dialogue context. We present an evaluation of the system using time-to-completion and the quality of the final solution that suggests that most native speakers of English can use the system successfully with virtually no training.

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 1 This paper presents a tripartite model of dialogue in which three different kinds of actions are modeled: domain actions, problem-solving actions, and dis-course or communicative actions. We contend that our process model provides a more finely differenti-ated representation of user intentions than previous models; enables the incremental recognition of com-municative actions that cannot be recognized from a single utterance alone; and accounts for implicit acceptance of a communicated proposition. 1

We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian) network to represent features of the domain that are needed to identify users' plans and goals. The application domain is a Multi-User Dungeon adventure game with thousands of possible actions and locations. We propose several network structures which represent the relations in the domain to varying extents, and compare their predictive power for predicting a user's current goal, next action and next location. The conditional probability distributions for each network are learned during a training phase, which dynamically builds these probabilities from observations of user behaviour. This approach allows the use of incomplete, sparse and noisy data during both training and testing. We then apply simple abstraction and learning techniques in order to speed up the performance of the most promising dynamic belief networks without a significant change in the accuracy of goal predictions. Our experi...

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.