K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL, pages 33--38, Berkeley, CA, 1991.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....as Select Recipe, only at the multi agent level. A group of agents select a recipe for a subgoal. Elaborate Group: The multi agent equivalent of Elaborate Individual. Using these four operators, a group of agents collaborates until it has completely specified a full SharedPlan. Lochbaum ([Lochbaum, 1991; Lochbaum, 1994; Lochbaum, 1998] developed an intentionrecognition algorithm based on the SharedPlan formalism and modeling the process of plan augmentation. Upon hearing an utterance, an agent ascribes certain intentions and beliefs to the speaker. If it is willing, the agent also adopts those ....

Karen E. Lochbaum, "An Algorithm for Plan Recognition in Collaborative Discourse," In Proceedings of the 29th ACL, pages 33--38, Berkeley, CA, June 1991.

....in all modalities and thus is a factor that must be reckoned with in developing more advanced systems for human machine communication. We have developed a model of collaborative planning, called SharedPlans, that provides a basis for human computer collaborative problem solving systems [45, 75, 73]. The formalization of SharedPlans [42] is being tested both as a component of dialogue systems [74] and in distributed AI systems [62] SharedPlans were developed initially to provide the intentional component of the model of discourse structure proposed by Grosz and Sidner (henceforth, G S) ....

K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29th Annual Meeting of the ACL, Berkeley, CA, 1991.

.... As a result, many discourse generation ideas are shared with work on plan recognition [Kautz 87, Hobbs et al. 88, Charniak Shimony 90] Several research efforts are investigating the nature and role of participants beliefs and intentions [Pollack 86, Cohen Levesque 90, Grosz Sidner 90, Lochbaum 91] and much effort is focused on the types of plans that underlie this type of discourse (see [Litman 85, Lambert Carberry 91, Ramshaw 91] Most of these theories postulate several levels of plans, each level handling a distinct phenomenon (discourse management, domain knowledge, etc. 4 ....

Lochbaum, K.E. 1991. An Algorithm for Plan Recognition in Collaborative Discourse. Proceedings of the 29th Annual Conference of the Association of Computational Linguistics, Berkeley (33--38).

....enabling or generating 4 the goal. However, this is too strong. In collaborating to achieve a mutual goal, participants sometimes propose an action that is not believed by the other participant or even the participant that 2 See also the subsequent work by Lochbaum, Grosz, and Sidner (1990) and Lochbaum (1991). 3 Their work also addresses a number of issues that we have not concerned ourselves with. First, we do not need to represent that an agent intends to perform an action or that it is able to execute the action (because the actions have already been performed) Second, we assume that agents have ....

Lochbaum, K. E. (1991). An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29 th Annual Meeting of the Association for Computational Linguistics, pages 33--38.

....only recognizes top level goals which is not sufficient for our purposes, and can only achieve polynomial time if the steps in the recipes are totally ordered, which is too restrictive for our domains. We believe Vilain s or other s fast recognition algorithms could be adapted to our formulation. Lochbaum (1991) presented a plan recognition algorithm based on the SharedPlan model of collaboration. Her plan recognizer does not chain recipes together, as our does, and thus performs only one level deep recognition. It does, however, make use of a wider range of relations by which actions contribute to ....

Lochbaum, K. E. (1991). An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL.

....opens the discussion on politeness by assuming that speakers are capable of doing means end reasoning. In contrast to the multi level approach to dialogue processing, Grosz, Sidner and Lochbaum only use domain level plans to model collaborative dialogue (Grosz Sidner 1986, Lochbaum et al. 1990, Lochbaum 1991, Lochbaum 1995) We agree with Lochbaum that it is better not to introduce multiple plan types, but: Although we have three plan libraries, only the object level and the metalevel plan libraries have functionally distinct roles. Our Agent Modeling plans aim at modeling intentional behavior in ....

Lochbaum, K.E. (1991). An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of ACL, pages 33--38, Berkeley,CA.

....behavior that is normal for such dialogues. 1. 2 Variable initiative The primary facility needed for variable initiative is the ability either to control the movements between subgoals (dialogue segments) or to release control and to follow the user s movements (Guinn, 1995; Kitano and Ess Dykema, 1991; Novick, 1988; Walker and Whittaker, 1990) Controlling the movement requires that the system have domain information available to guide decisions concerning which directions may be good to take. Having made these decisions, the system then jumps to the associated subdialogs and follows its plan ....

K.E. Lochbaum. 1991. An algorithm for plan recognition in collaborative discource. In Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, pages 33--38.

....as the transitive closure of the various one step links that appear in the act type relation ontology. Lochbaum et al. note that the belief 103 ascription process is defeasible, and indicate that argumentation as in [Konolige and Pollack, 1989] is one way of performing such reasoning. Lochbaum [Lochbaum, 1991] describes an algorithm for explaining the role of a particular activity in an augmented recipe. The approach seems very similar to the constraint based search used by my implementation of recognition (cf. Section 4.5.2) Again, I think that the use of the formal system of defeasible reasoning ....

Karen E. Lochbaum, "An algorithm for plan recognition in collaborative discourse," in Proceedings of the Twenty-Ninth Annual Meeting of the Association for Computational Linguistics, pages 33--38, Berkeley, CA, 18--21 June 1991. University of California.

....our research. Grosz and Sidner [48] introduce the notion of a shared plan to capture certain phenomena of collaborative behavior. However, they do not provide a concrete plan recognition process or implementation. Initial work on the required plan recognition algorithm is described in Lochbaum [72]. Clark and Wilkes Gibbs [23] provide results from a study undertaken to see how people collaborate and coordinate in providing definite references. They propose the following principle of behavior: The participants in a conversation try to establish, roughly by the initiation of each new ....

K.E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, pages 33--38, 1991.

....by the discourse level, instead of how they are conveyed (by an Inform action, by expressing doubt, etc. Related Work Allen (1991) proposed different plan modalities that capture the shared and individual beliefs during collaboration, and Grosz, Sidner and Lochbaum (Grosz Sidner 1990; Lochbaum 1991) proposed a SharedPlan model for capturing intentions during a collaborative process. However, they do not address response generation during collaboration. Litman and Allen (1987) used discourse meta plans to handle correction subdialogues. However, their CorrectPlan only addressed cases in which ....

Lochbaum, K. 1991. An algorithm for plan recognition in collaborative discourse. In Proceedings of the ACL, 33--38.

....belief and also provide its evidence against the belief, leading to the generation of the following utterances: 11) S: Why do you think Dr. Smith postponed his sabbatical until 1996 (12) Isn t he spending next year at IBM 5 Related Work Grosz, Sidner and Lochbaum [Grosz and Sidner, 1990, Lochbaum, 1991] developed a SharedPlan approach to modelling collaborative discourse, and Sidner [Sidner, 1994] formulated an artificial language for modeling such discourse. Sidner viewed a collaborative planning process as proposal acceptance and proposal rejection sequences. Her artificial language treats ....

Karen E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29th ACL, pages 33--38, 1991.

....this paper is based on Grosz and Kraus s definitions. Figure 6 contains a high level schematic of the full SharedPlan definition, while Table 1 provides a summary of the operators used in Grosz and Kraus s definitions and their interpretations. In previous work (Lochbaum, Grosz, and Sidner, 1990; Lochbaum, 1991), we presented algorithms for augmenting the beliefs and intentions of an evolving SharedPlan for some act ff on the basis of utterances concerning the actions that need to be performed to accomplish ff. These utterances are understood as directed towards establishing the recipe the agents will ....

....to model the context dependent nature of parameter identification. This function returns a suitable identification constraint (Appelt and Kronfeld, 1987) for a parameter p i in the context of an act type ff. For example, 8 In previous work (Balkanski, 1990; Lochbaum, Grosz, and Sidner, 1990; Lochbaum, 1991), recipes were informally defined as act types and relations among them. In the new formulation of a recipe as a set of constituent acts and constraints on those acts, the relations are represented by the constraints. in the case of sending a letter to John s residence, the constraint produced ....

[Article contains additional citation context not shown here]

Lochbaum, K. E. 1991. An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29th Annual Meeting of the ACL, pages 33--38, Berkeley, CA.

....bringing about the condition marked (a) a) Figure 5: Analysis of the second subdialogue in Figure Understanding Utterances Within Segments When a speaker produces an utterance within a segment, a hearer must determine why the speaker said what he did. In previous work (Lochbaum et al. 1990; Lochbaum, 1991), we presented algorithms for augmenting the beliefs and intentions of an evolving SharedPlan for some act ff on the basis of utterances concerning the actions that need to be performed to accomplish ff. These algorithms model the hearer s reasoning by trying to ascribe appropriate beliefs to the ....

K. E. Lochbaum. 1991. An algorithm for plan recognition in collaborative discourse. In Proceedings of the 29th Annual Meeting of the ACL, pages 33--38, Berkeley, CA.

No context found.

K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL, pages 33--38, Berkeley, CA, 1991.

No context found.

K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL, Berkeley, CA, 1991.

No context found.

K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL, Berkeley, CA, 1991.

No context found.

K. E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proc. 29th Annual Meeting of the ACL, pages 33--38, Berkeley, CA, 1991.

No context found.

Karen E. Lochbaum, \An Algorithm for Plan Recognition in Collaborative Discourse," In Proceedings of the 29th ACL, pages 33-38, Berkeley, CA, June 1991.

No context found.

Karen E. Lochbaum. An algorithm for plan recognition in collaborative discourse. In Proceedings of ACL-91, Berkeley, 1991.

No context found.

Karen Lochbaum. An Algorithm for Plan Recognition in Collaborative Discourse. In ACL91, Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, pages 33--38, 1991.

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