Heeman, P. 1991. A computational model of collaboration on referring expressions. M.Sc. thesis, Dept. of Computer Science, University of Toronto.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....1996, 1998) relatively little work has focused on exploiting uncertainty; for example, by explicitly quantifying uncertainty in terms of probabilities at each level. The framework we present broadens the scope of previous models of grounding and referential expressions (Edmonds, 1993; Heeman, 1991; Heeman Hirst, 1992; Hirst et al. 1994) by highlighting the efficacy of Bayesian networks and decision theory to reason about uncertainty before and during misunderstanding. Furthermore, the introduction of decision theory allows systems to use expected utility to provide fine grain, ....

Heeman, P. 1991. A computational model of collaboration on referring expressions. M.Sc. thesis, Dept. of Computer Science, University of Toronto.

....and later acknowledged. In fact, making reference to an item in a DU initiated by the other agent can be a means of acknowledging that thread. In this manner, we can also model the collaborative nature of the referring process itself, in a manner similar to [ Clark and Wilkes Gibbs, 1986; Heeman, 1991 ] 13 6 Other Issues Space precludes a detailed explanation of how other contextual features are represented and used by other system modules, but we briefly note some of the issues here. Dialogue Management The theory of context representation outlined above can also serve as a basis for ....

Heeman, P. A. 1991. A computational model of collaboration on referring expressions. Master 's Thesis, Technical Report CSRI 251, Department of Computer Science, University of Toronto.

....for listening and speaking. The opposite case is represented by a person who is knowledgeable or skilled with regard to a particular task. By 1 Although Bolinger [Bol58] states that the use of a rising pitch to mark new information is universal across languages. 2 Following [Bre90] and Heeman [Hee91] the speaker is denoted by female pronouns, the hearer by male. This imperfect usage replaces the more imperfect usage offered by current American English. definition, this person is in possession of numerous and salient facts about the task. By the same token, she has a large attentional ....

Peter Anthony Heeman. A Computational Model of Collaboration on Referring Expressions. Technical Report CSRI--251, Computer Systems Research Institute, University of Toronto, Canada, 1991.

....is not believed by the other agent, or even believed by himself to contribute. Without being able to incorporate these types of proposals into the shared plan, the model cannot represent the state in which an agent understands how an utterance contributes to the plan, while not agreeing with it. Heeman (1991) suggests that the only requirement for a shared plan is that it not be incoherent. 2.5 Implementation Details of Heeman s System Since we are building upon Heeman s (1991) implementation, we describe the pertinent details here, thus avoiding a lengthy discussion later in the thesis. The system ....

....cannot represent the state in which an agent understands how an utterance contributes to the plan, while not agreeing with it. Heeman (1991) suggests that the only requirement for a shared plan is that it not be incoherent. 2. 5 Implementation Details of Heeman s System Since we are building upon Heeman s (1991) implementation, we describe the pertinent details here, thus avoiding a lengthy discussion later in the thesis. The system is implemented in Prolog. The three central modules are the plan construction module, the plan inference module, and the belief module. We will describe each in turn, ....

[Article contains additional citation context not shown here]

Heeman, P. A. (1991). A computational model of collaboration on referring expressions.

....understanding utterances, not with generating appropriate responses. The work in [5, 11, 9] addressed generating cooperative responses and responding to plan based misconceptions, but did not capture these within an overall collaborative system that must negotiate proposals with the user. Heeman [4] used meta plans to account for collaboration on referring expressions. We have addressed collaboration in constructing the user s task related plan, captured cooperative responses and negotiation of how the plan should be constructed, and provided an accounting for why a user s question may never ....

Peter Heeman. A computational model of collaboration on referring expressions. Master's thesis, University of Toronto, 1991.

....if they are poorly written or expressed; highquality language generation is very difficult for people. Nevertheless, people are, in general, quite successful in their use of language. That s because they have strategies This paper summarizes work reported in greater detail in references [15, 20, 21, 22, 27, 28]. y Susan McRoy is now at the Department of Electrical Engineeringand Computer Science, University of Wisconsin Milwaukee, Milwaukee, WI 53201, U.S.A. z Peter Heeman is now at the Department of Computer Science, University of Rochester, Rochester, NY 14627, U.S.A. for coping with their ....

....goals to adopt. The surface actions of the constructed plans form the response of the system. The system then switches back to the role of hearer and waits for a response from the other copy. In the rest of this section, we give a brief overview of the model; details may be found in references [20, 21]. 3.3 Plans for referring We extend the earlier approaches of Cohen [9] and Appelt [2] in planning not only the occurrence of a referring expression but also, at the same level, its content. We use a surface speech action, s refer, to express the speaker s intention to refer, and a surface ....

[Article contains additional citation context not shown here]

Heeman, Peter A. A computational model of collaboration on referring expressions. MSc thesis, published as technical report CSRI-251, Department of Computer Science, University of Toronto.

No context found.

Peter A. Heeman (1991), A computational model of collaboration on referring expressions. MSc thesis, published as technical report CSRI-251, Department of Computer Science, University of Toronto.

....of the constructed plans form the response of the system. The system then takes its turn as hearer and waits Hirst et al.: Repairing converational misunderstandings 7 for a response from the other copy. In the rest of this section, we give a brief overview of the model; details are given by Heeman (1991) and Heeman and Hirst (1994) 3.3 Plans for referring We extend the earlier approaches of Cohen (1981) and Appelt (1985b) in planning not only the occurrence of a referring expression but also, at the same level, its content. We use a surface speech action, s refer, to express the speaker s ....

....the case of when the referring expression overconstrains the choice of referent. He uses heuristics to relax the constraints of the description and to pick one that nearly fits it. This problem is beyond the scope of this research, and so we simply choose one of the referents arbitrarily (but see Heeman (1991) for how a simplified version of Goodman s algorithm that only relaxes a single constraint can be incorporated into the planning paradigm) The second step is to refashion the referring expression so that it identifies the candidate chosen in the first step. This is done by using plan repair ....

Heeman, Peter A. (1991). A computationalmodel of collaboration on referring expressions. MSc thesis, published as technical report CSRI-251, Department of Computer Science, University of Toronto.

....Action Schemas This section presents action schemas for referring expressions. We omit discussion of actions that account for superlative adjectives, such as largest , that describe an object relative to the set of objects that match the rest of the description. A full presentation is given by Heeman (1991). As we mentioned, the action for referring, called refer, is mapped to the surface speech actions through the use of intermediate actions and plan decomposition. All of the reasoning is done in the refer action and the intermediate actions, so no constraints or effects are included in the ....

....for the case of when the referring expression overconstrains the choice of referent. He uses heuristics to relax the constraints of the description and to pick one that nearly fits it. This problem is beyond the scope of this paper, and so we choose one of the referents arbitrarily (but see Heeman (1991) for how a simplified version of Goodman s algorithm that relaxes only a single constraint can be incorporated into the planning paradigm) The second step is to refashion the referring expression so that it identifies the candidate chosen in the first step. This is done by using plan repair ....

[Article contains additional citation context not shown here]

Heeman, Peter Anthony. 1991. A computational model of collaboration on referring expressions.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC