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.

Abstract not found

We use the idea that actions performed in a conversation become part of the common ground as the basis for a model of context that reconciles in a general and systematic fashion the differences between the theories of discourse context used for reference resolution, intention recognition, and dialogue management. We start from the treatment of anaphoric accessibility developed in DRT, and we show first how to obtain a discourse model that, while preserving DRT's basic ideas about referential accessibility, includes information about the occurrence of speech acts and their relations. Next, we show how the different kinds of `structure' that play a role in conversation -- discourse segmentation, turn-taking, and grounding -- can be formulated in terms of information about speech acts, and use this same information as the basis for a model of the interpretation of fragmentary input.

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.

This paper shows how agents' choice in communicative action can be designed to mitigate the effect of their resource 1/mits in the context of particular features of a collaborative planning task. I first motivate a number of hypotheses about effective language behavior based on a statistical analysis of a corpus of natural collaborative planning dialogues. These hypotheses are then tested in a dialogue testbed whose design is motivated by the corpus analysis. Experiments in the testbed examine the interaction between (1) agents' resource 1/mits in attentional capacity and inferential capacity; (2) agents' choice in communication; and (3) features of communicative tasks that affect task difficulty such as inferential complexity, degree of belief coordination required, and tolerance for errors. The results show that good algorithms for communication must be defined relative to the agents' resource 1/mits and the features of the task. Algorithms that are inefficient for inferentially simple, low coordination or fault-tolerant tasks are effective when tasks require coordination or complex inferences, or are fault-intolerant. The results provide an explanation for the occurrence of utterances in human dialogues that, prima facie, appear inefficient, and provide the basis for the design of effective algorithms for communicative choice for resource limited agents.

This paper introduces the special issue of Knowledge-Based Systems on HumanComputer Collaboration (HCC). It derives a set of fundamental issues from a definition of collaboration, introduces two major approaches to HCC, and surveys each approach, showing how it formulates and addresses the issues. It concludes by proposing some themes that should characterize a unified approach to human-computer collaboration. 1 Introduction Collaboration is a process in which two or more agents work together to achieve shared goals. Thirty researchers came together in Raleigh, North Carolina in October of 1993 for a AAAI Fall Symposium dedicated to this topic. The goal of the symposium was to achieve a better understanding of Human-Computer Collaboration (HCC), collaboration involving at least one human and one computational agent. In particular, the symposium sought to explore the fundamental nature of collaborative problem solving, understand the constraints brought to bear by the differing charac...

In cooperative man-machine interaction, it is necessary but not sufficient for a system to respond truthfully and informatively to a user's question. In particular, if the system has reason to believe that its planned response might mislead the user, then it must block that conclusion by modifying its response. This paper focusses on identifying and avoiding potentially misleading responses by acknowledging types of "informing behavior " usually expected of an expert. We attempt to give a formal account of several-types of assertions that should be included in response to questions concerning the achievement of some goal (in addition to the simple answer), lest the questioner otherwise be misled. 1. Introduction] In cooperative man-machine interaction, it is necessary but not sufficient for a system to respond truthfully and informatively to a user's question. In particular, if the system has reason to believe that its planned response might mislead the user to draw a false conclusion, then it must block that conclusion by modifying or adding to its response.

Conversations involve all sorts of verbal activities beyond those strictly related to the performance of the task at hand. Among other things, the participants in a conversation have to make sure they both understand what's going on, to manage turn taking, and to keep each other informed about their progress in achieving their task. The participants share information about the status of all of these processes; this suggests that the view of the conversational score they share is rather more complex than assumed in previous accounts. We proposed a preliminary formalization of this more complex view of the conversational score in previous work; in this paper we revise that earlier model, and use our theory of the conversational score to give a partial specification of the effect of the dialogue acts included in the DRI classification.

Abstract not found

The effectiveness of simulation-based training for individual tasks -- such as piloting skills -- is well established, but its use for team training raises challenging technical issues. Ideally, human users could gain valuable leadership experience by interacting with synthetic teammates in realistic and potentially stressful scenarios. However, creating human-like teammates that can support flexible, natural interactions with humans and other synthetic agents requires integrating a wide variety of capabilities, including models of teamwork, models of human negotiation, and the ability to participate in face-to-face spoken conversations in virtual worlds. We have developed such virtual humans by integrating and extending prior work in these areas, and we have applied our virtual humans to an example peacekeeping training scenario to guide and evaluate our research. Our models allow agents to reason about authority and responsibility for individual actions in a team task and, as appropriate, to carry out actions, give and accept orders, monitor task execution, and negotiate options. Negotiation is guided by the agents' dynamic assessment of alternative actions given the current scenario conditions, with the aim of guiding the human user towards an ability to make similar assessments.