Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200, 1987.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Carberry s system first generated all possible interpretations and then filtered among them, making it vulnerable to a possible runtime explosion in a larger domain. Our system uses context first to decide which options to explore. 4. 4 Dialogue and Domain Plans Litman and Allen [Lit85, Lit86, LA87, LA90] extended Carberry s and Allen s work to better account for various dialogue phenomena. Although a dialogue s focus is on the domain, there seem to be several meta layers which help ensure robust communication. Essentially, Litman and Allen added a new layer to the plan recognition system, ....

D. J. Litman and J. F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163--200, 1987.

....Hiroaki Kitano and Carol Van Ess Dykema t Center for Machine Translation Carnegie Mellon University Pittsburgh, PA 15213 hiroaki cs.cmu.edu ABSTRACT This paper presents an enhanced model of plan based dialogue understanding. Most plan based dialogue understanding models derived from [Litman and Allen, 1987] as sume that the dialogue speakers have access to the same domain plan library, and that the active domain plans are shared by the two speakers. We call these features shared domain plan consflaints. These assumptions, however, are too sflict to account for mixed initiative dialogues ....

....those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S. Department of Defense or of the United States government. vaness cs.cmu.edu The existing plan based model of dialogue under standing (as represented by [Litman and Allen, 1987]) accounts for dialogues in which a single speaker con trols the initiative. We call these dialogues Single Initiative Dialogues. In modeling single initiative dialogues, Litman and Allen assume a shared stack that represents a joint plan (joint domain plan) This joint plan is shared by the two ....

[Article contains additional citation context not shown here]

Litman, D. and Allen, J., "A Plan Recognition Model for Subdialogues in Conversation ", Cognitive Science 11 (1987), 163-200.

....acts needs to provide a solution to questions such as these. But, such questions are not merely of theoretical interest. Natural language database questionanswering systems have been known to receive performative utterances [14] dialogue systems that recognize illocutionary acts (e.g. 6] will need to infer the correct illocutionary force to function properly, dialogue translation systems [5] will have to cope with markers of illocutionary 79 force that function performatlvely (e.g. sentence final particles in Japanese) and proposals for agent oriented programming languages ....

....(addr) and what kind of sentence (s) has been spoken (indicated by ) We shall assume that everyone knows that a given utterance is of a given syntactic type (e.g. declarative) that speakers and addressees are observers, and that observers are known by all to be observing. 7 Definition 6 a spkr, obs, addr, e, s, n (KNOW ohs (DONE spkr e) A (UTTER spkr addr s e) A (q s) A (ABEL nobs spkr (BEFORE (GOAL spkr [AFTER (KNOW addr (BEFORE ) D (ABEL n ohs spkr (BEFORE a A (GOAL spkr [AFTER (KNOW addr (BEFORE a) That is, is an abbreviation for a quantified ....

[Article contains additional citation context not shown here]

D.J. Litman and J. F. Allen. A plan recogni- tion model for subdialogues in conversation. Technical report, Department of Computer Science, Univ. of Rochester, Rochester, New York, November 1984.

....is the process of inferring an agent s plan from observation of the agent s actions. The agent s actions can be physical actions or speech actions. Four principal methods for plan recognition have been proposed in the literature. The methods are plausible inference (Allen [1] Carberry [2] Litman [15], Sidner [25] parsing (Huff and Lesser [9] circumscribing a hierarchical representation of plans and using deduc tion (Kautz [12, 13] and abduction (Charniak and McDermott [6] Konolige and Pollack [14] Poole Our particular interest is in the use of plan recognition in question answering ....

.... on sali ence heuristics to solve the ambiguity problem [e.g. 1, 2, 17, and see the final section] Existing propo sals for resolving ambiguity beyond heuristics are underspecified and what usually underlies these proposals is the assumption that we always want to determine one unique plan [2, 15, 19, 25]. We show how to relax the assumption that the plan recognition component returns a single plan. That is, given that the result of the plan recognition phase will usually be a disjunction of possible plans, we show how to design a response component to generate cooperative responses given the ....

[Article contains additional citation context not shown here]

Litman, D. J., and J. F. Allen. 1987. A Plan Recognition Model for Subdialogue in Conversations. Cognitive Science 11, 163-200.

....is being invoked. Thus, expectations are one of the primary mechanisms needed for tracking the conversation as it jumps from subdialog to subdialog. This is known elsewhere as the plan recognition prob lem and it has received much attention in re cent years. See, for example, Allen, 1983] [Litman and Allen, 1987], Pollack, 1986] and [Carberry, 1990] Systems capable of all of the above behaviors are rare as has been observed by [Allen el al. 1989] no one knows how to fit all of the pieces together. One of the contributions of the current work is to present an architecture that can provide them all ....

D.J. Litman and J.F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163-200, 1987.

.... TO USER QUERIES IN A COLLABORATIVE ENVIRONMENT Jennifer Chu Department of Computer and Information Sciences University of Delaware Newark, DE 19716, USA Internet: jchu cis.udel.edu Abstract We propose a plan based approach for responding to user queries in a collaborative environment. We ague that in such an environment, the system should not accept the user s query automatically, but should consider it a proposal open for ....

....following utterances by Lainbert s plan recognition algorithm modified to accommodate the separation of the existing and proposed dialogue models, and augmented with a relaxation algorithm to recognize ill formed plans[2] U: I want to satisfy my seminar course requirement. Who s teaching CS6897 3 The Evaluator A collaborative system should only incorporate proposed actions into an existing plan if they are considered appropriate. This decision is made by the evaluator, which will be discussed in this section. This paper only considers cases in which the user s proposal contains an ....

[Article contains additional citation context not shown here]

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Sci- ence, 11:163--200, 1987.

....transaction level, an exchange level, an intervention level modeling initiative, reaction and evaluation, and finally a level consisting of dialogue acts. The system has been developed for the domain of flight reservations. Plan oriented approaches for dialogue modeling are described in Litman and Allen (1987) and Lambert and Carberry (1992) Both approaches distinguish domain or task, problem solving and discourse levels. Knowledge from the various levels is employed to solve the task of plan recognition in dialogues. Connections do not only exist between the various levels but also between elements ....

....the task of plan recognition in dialogues. Connections do not only exist between the various levels but also between elements within one level. These links are modeled either as dis course plans which follow the course of the interaction (e.g. CONTINUATION, CLAKIFICATION and TOPIC SHIFT, see Litman and Allen (1987)) or as discourse actions that link an utterance with the context. A similar distinction of various levels of representation is made in O Donnell (1990) except that the links between various elements of his discourse or exchange model are not made explicit. The EES project (Explainable Expert ....

Diane J. Litman and James F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11:163-200, 1987

....dialogue incrementally builds a structure of the discourse (a Dialogue Model, or DM) using a multi level belief model updated after each utterance. The belief model contains the beliefs as cribed to the user during the course of the conversation and how strongly each belief is held. Researchers [1, 3, 5] have noted that discourse understanding can be enhanced by recognizing a user s goals, and that this recognition process requires reasoning about the agent s beliefs [7] For example, in order to recognize from utterance IS2 in the following dialogue that the speaker has the communicative goal of ....

....for recognizing utterances that involve negotiation dialogues. Without the ability to modify a belief model as a dialogue progresses, it would not be possible to plausibly ascribe 1) or 3) so it is unclear how recognizing expressions of surprise would be accomplished in systems such as Litman s [5] that recognize discourse goals but do not maintain belief models. IS also exemplifies how people may have levels of belief and indicate those levels in the 1 This material is based upon work supported by the National Science Foundation under Grant No. IRI 8909332. The Govern ment has certain ....

[Article contains additional citation context not shown here]

D. Litman and J. Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163- 200, 1987.

....Also, Carberry s system rst generated all possible interpretations and then ltered among them, making it vulnerable to a possible runtime explosion in a larger domain. Our system uses context rst to decide which options to explore. 4. 4 Dialogue and Domain Plans Litman and Allen [Lit85, Lit86, LA87, LA90] extended Carberry s and Allen s work to better account for various dialogue phenomena. Although a dialogue s focus is on the domain, there seem to be several meta layers which help ensure robust communication. Essentially, Litman and Allen added a new layer to the plan recognition system, ....

D. J. Litman and J. F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163-200, 1987.

....for dialogues describing complex plans, it only worked for utterances that talked directly about actions and goals in a domain. Other dialogue phenomena (such as correction and clarification subdialogues) were not addressed. Dialogue and Domain Plans Litman and Allen ( Litman, 1985; Litman, 1986; Litman and Allen, 1987; Litman and Allen, 1990] extended Carberry s earlier work to better account for various dialogue phenomena. Although a dialogue s focus is on the domain, there seem to be several meta layers which help ensure robust communication. Essentially, Litman and Allen added a new layer to the ....

Diane J. Litman and James F. Allen, "A Plan Recognition Model for Subdialogues in Conversations," Cognitive Science, 11(2):163--200, 1987.

....form it is a sequence of messages in which, after the initial message, each is a direct response to the previous one. More complicated structures occur when subdialogs are needed. Linguistics and philosophers have not come to any consensus about subdialogs, but several types consistently appear (Litman Allen 1987; Moore 1998b; Polanyi 1988) subordinations, corrections, and interruptions. A message begins a subordinate conversation when it elaborates on a point made in a previous message. This message should be about the previous message, probably as a clarification of some fact. A message that begins a ....

Litman, D. J., and Allen, J. F. 1987. A plan recognition model for subdialogues in conversations. Cognitive Science 11:163--200.

....1962) was to connect speech acts with other actions. However different theories may maintain a crisp or more blurred distinction between dialogue acts and non communicative acts. Some want a clear distinction, while others would want to use the same logic of action account to account for both. (Litman and Allen, 1987) distinguished dialogue acts as being meta acts, defining discourse plans as having other plans (domain or discourse) as parameters. Lambert and Carberry, 1991) also distinguish discourse, domain and problem solving plans and actions. Depending on the answer to question 8, some may want to ....

Litman, D. J. and Allen, J. F. (1987). A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200.

.... To obtain new partitions (clusters) of the set of documents that the user selected with his query(ies) To use domain knowledge whenever is possible. 2 Dialogues Dialogues in the context of information retrieval systems are di erent from traditional dialogues in computational linguistics [LA87, Pol90, CCC98, CL99, MP93, Loc98] because our user normally does not have a plan to execute, he actually does not have a precise goal such as: go to Boston or phone to Mary . Our users may want to see some documents, but they do not know which particular documents. The function of our dialogue system is to help a user de ning ....

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11(1), 1987.

....of documents selected by the user query in order to help the user in the refinement of his query. In order to accomplish this goals we need: To record the previous user interaction with the system (user questions and the system answers) This record will play the role of a dialogue structure [CL99,RL93,LA87]. It provides the context of sentences (questions and answers) CCC98,Wal96] allowing the system to solve some discourse phenomena such as anaphoras and ellipses. Since our system is multimodal, other user acts such as button clicks and menu choices are also represented in our dialogue ....

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11(1), 1987.

.... To obtain new partitions (clusters) of the set of documents that the user selected with his query(ies) To use domain knowledge whenever the system has it. Dialogues in the context of information retrieval systems are di erent from traditional dialogues in computational linguistics [9, 13, 3, 2, 10] because our user normally does not have a plan to execute, he actually does not have a precise goal such as: go to Boston or phone to Mary . Our users may want to see some documents, but they do not know which particular documents. The function of our dialogue system is to help a user de ning ....

....they provide information on user intentions; and knowledge of the text database, this knowledge is obtained from di erent ways using the same sources (documents) and domain rules in a knowledge base. In traditional dialogues the system must recognize the user goals and his plans to achieve them[9, 13, 3]. The system represents and infers the user intentions using domain knowledge from a library of plans and checking if a plan is correct. The discourse structure of this kind of dialogues is complex, it has many kinds of segments: continuation, elaboration, repair, clari cation, etc. and their ....

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11(1), 1987.

....system to infer user intentions and attitudes and the ability to represent the dialogue sentences in a dialogue structure. The dialogue structure will be kept in the user database. Note that dialogues in information retrieval systems [LJ94] are di erent from dialogues in computational linguistics [LA87, Pol90, CCC98, CL99, MP93, Loc98] because our user normally does not have a plan to execute, he actually does not have a precise goal such as: go to Boston or phone to Mary . Our users may want to see some documents, but they do not know which particular documents. The Domain Level includes ....

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11(1), 1987.

....Model The task model relates to the typical actions carried out by a user in a given application type. The task should be matched by the functionality of the system. A task can be expressed by a hierarchy of goals and sub goals, or else by a plan, a combination of actions, to achieve those goals (Litman and Allen, 1987; Carberry, 1990) For dialogue systems, the basic actions from which complex plans can be constructed are either database operations or dialogue acts like requests or assertions. The task constrains the dialogue in two ways. First, the task determines what objects are relevant. The attributes ....

.... content related aspects of coherence, namely consistence, relevance, informativeness and licensing can be given a formal semantics in terms of a set of possibilities that are structured by issues or contextual questions (Groenendijk, 1999; Hulstijn, 2000) In a plan recognition framework such as (Litman and Allen, 1987; Carberry, 1990) the task related aspects can be characterised in terms of plans and goals. The interaction related aspects are dealt with either in terms of dialogue games, or in terms of coherence relations and default principles for coherent attachment (Asher and Lascarides, 1998) There are ....

Litman, D. L. and Allen, J. F. (1987). A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200.

....B is an assertion related to another subgoal on the theorem proving tree as shown in Figure 1. The user may initiate such a change in subdialogue in an attempt to pursue another path to the global goal. Here the machine first must track the user s intention (in a process called plan recognition [15, 16, 17, 18, 19]) and then evaluate whether to follow the move or not. This decision is based upon the current level of the initiative of the system as described below. If the system follows the user s initiative, it will apply its internal theorem proving system to the subgoal E and pursue voice interactions ....

D.J. Litman and J.F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163-- 200, 1987.

....mechanisms and negotiation strategies require the ability to detect differences between an agent s plan and that of its collaborator. These mechanisms are rendered almost useless without this ability. However, plan recognition is one of the more difficult problems facing intelligent agents [18, 13, 4, 6, 1]. In domains where the agent has limited knowledge, mistakes in plan recognition will be common. Utterances that explicitly outline the plan an agent is taking can assist greatly in this process. Our research focuses on the announcement of certain goal failures. Suppose an agent insists on ....

D.J. Litman and J.F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163--200, 1987.

....acts needs to provide a solution to questions such as these. But, such questions are not merely of theoretical interest. Natural language database questionanswering systems have been known to receive performative utterances [14] dialogue systems that recognize illocutionary acts (e.g. [6]) will need to infer the correct illocutionary force to function properly, dialogue translation systems [5] will have to cope with markers of illocutionary force that function performatively (e.g. sentence final particles in Japanese) and proposals for agent oriented programming languages [7, ....

D. J. Litman and J. F. Allen. A plan recognition model for subdialogues in conversation. Technical report, Department of Computer Science, Univ. of Rochester, Rochester, New York, November 1984.

....recognition in terms of a set of plan recognition rules together with a heuristic control strategy, but gave no theoretical foundation to his rules of plausible inference. Extended Discourse Litman and Allen built an extension of the Discourse system, firstly built by Allen and Perrault in 1980 [16]. Litman s plan recognition algorithm constructs a stack of partially recognised plans. When a new action is observed, the system tries to attach it to the stack of partially recognised plans. However this system does not allow a disjunction of different possible plans. If the interpretation ....

Litman D., Allen J. (1984). A Plan Recognition Model of Subdialogues in Conversations. TR 141, Department of Computer Science, University of Rochester, NY.

....its argument anyway. Handle subdialogues (U4) Conversational partners normally probe each other s arguments to decide which parts of an argument to accept. This may be done by means of different types of subdialogues, e.g. information sharing [Chu Carroll and Carberry, 1995] or clarification [Litman and Allen, 1987]. In our example, the user poses an exploratory what if query to speculate on the effect of a particular event on the argument goal. Track focus (U5) This utterance may be interpreted as an exploratory query to consider the effect of Wayne Carey on the argument goal or as a shift in topic, ....

....goal. Track focus (U5) This utterance may be interpreted as an exploratory query to consider the effect of Wayne Carey on the argument goal or as a shift in topic, where the focus is now on Carey s health. Both interpretations should be considered, and a preferred interpretation selected [Litman and Allen, 1987, Raskutti and Zukerman, 1991] In this example, the former interpretation is (erroneously) selected. Recover from misunderstandings (U6, S6) U5 was previously interpreted as a query about the effect of Wayne Carey on the argument goal. However, when the user indicates that this is not his or ....

[Article contains additional citation context not shown here]

Litman, D. and Allen, J. F. (1987). A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200. 16

.... systems that perform simple tasks in specific domains (e.g. 7, 5, 1] or on developing algorithms that model specific dialogue phenomena that often take place in naturally occurring human human dialogues, such as recognizing and initiating negotiation and clarification subdialogues (e.g. [6, 9, 4, 2]) Systems in the former category are often heavily handcrafted, and therefore require substantial effort to be ported to perform similar functions in new domains. While systems in the latter category utilize general algorithms that apply across domains, they often require sophisticated modeling ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200, 1987.

....and each action is composed by an head, pre conditions, constraints, e ects and sub actions. The inference of plans (a list of user actions) is done through the use of a library of plans and actions, some heuristic rules and the user possible goals. This approach has been used by Litman and Allen ([7, 6]) in order to infer plans behind speech acts in dialogues. A di erent approach was followed by Pollack ( 11, 1] which models plan as mental states and tries to abduct the mental attitudes behind each speach act. In this paper we follow a general approach which will allow us to handle both ....

....(it is a cooperative dialogue) and to know that the hearer wants the action to be done. There were also de ned meta actions, allowing the inference of meta plans and allowing the system to reason about the structure of the dialogue: continue plan, identify parameter, correct plan and modify plan ([7, 6]) As an example of the translation process into extended logic programs, it is shown the result of this process for the request speech act: suceeds(E) act(E; request(s; h; a) 5) holds at(want(s; a) E) holds at(surface request(s; h; a) E)or holds at(surface request(s; h; informif(h; ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163-200, 1987.

....and each action is composed by an head, pre conditions, constraints, e ects and sub actions. The inference of plans (a list of user actions) is done through the use of a library of plans and actions, some heuristic rules and the user possible goals. This approach has been used by Litman and Allen ([6, 5]) in order to infer plans behind speech acts in dialogues. A di erent approach was followed by Pollack ( 10, 1] which models plan as mental states and tries to abduce the mental attitudes behind each speech act. In this paper we follow a general approach which will allow us to handle both ....

.... request(s; h; a) 16) initiates(E; know(h; want(s; a) act(E; request(s; h; a) 17) There were also de ned meta actions, allowing the inference of meta plans and allowing the system to reason about the structure of the dialogue: continueplan, identify parameter, correct plan and modify plan ([6, 5]) After this process the rst user utterance can generate the following facts: 1. happens(e1) 2. act(e1, surface request(p, c, informref(c, p, T, train(montreal) 3. holds at(knowref(p, time(8:50) train(montreal) e1) describing that the passenger requested to be informed by the clerk ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163-200, 1987.

....We use as our basis the model proposed by Clark and Wilkes Gibbs (1986) In their work, they give a descriptive 1 account of the conversational moves that participants make when collaborating to make a referring expression. In making it computational, we draw on the insights of Appelt (1985a) Litman and Allen (1987), and Pollack (1986) and propose a model based on the planning paradigm. From Appelt, we use the idea that the act of referring can be incorporated into a plan based model of how agents construct utterances. From Litman and Allen, we use the idea that meta plans can account for how conversational ....

....action calls the algorithm that was mentioned in section 2.2.1 to choose a description that satisfies the preconditions. The chosen description is then used by the grammar to determine the linguistic realization of the noun phrase. 13 2.4. 4 Discourse Plans and Clarification Subdialogues Litman and Allen (1987) have taken a plan based approach to understanding discourse. In addition to using domain plans to encode knowledge about the topic of conversation, they use discourse plans to encode knowledge about conversations. Discourse plans correspond to how an utterance can relate to the current topic of ....

[Article contains additional citation context not shown here]

Litman, D. J. and Allen, J. F. (1987). A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163--200.

....as a sequence of actions and each action is composed by a head, preconditions, constraints, e ects and sub actions. The inference of plans is done through the use of a library of plans and actions, some heuristic rules and the user possible goals. This approach has been used by Litman and Allen ([9, 8]) in order to infer plans behind speech acts in dialogues. Another approach has been followed by [2] and uses weighted abductive reasoning taking interpretation as an abductive process ( 7] We also take interpretation as abduction but, in contrast to the weighted abduction approach, we propose ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163-200, 1987.

....actions and each action is composed by a head, preconditions, constraints, e ects, and subactions. The inference of plans (a list of user actions) is achieved by using a library of plans and actions, some heuristic rules, and the user possible goals. This approach has been used by Litman and Allen [10, 9] in order to infer plans behind speech acts in dialogues. A di erent approach was followed by Pollack [14, 2] which models plans as mental states and tries to abduce the mental attitudes behind each speech act. We propose a general extended logic programming framework which will allow us to ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163-200, 1987.

....inferred the goals of the other person and a portion of that person s plan for achieving those goals. This is often referred to as plan recognition. Plan recognition has been used extensively in a wide variety of computer systems. Applications include language understanding and response generation[AP80, PA80, LA87, Car90b, SB92, SHB95, HS96], speech to speech translation[Ale95] interfaces for computer aided design[GL92] UNIX help systems[May92] collaborative problem solving[LRS99] and automated descriptions of image sequences[RS91] One might ask whether plan recognition is performed by humans or is just an artifact of use in ....

....for resolving conflict between two competing goals. Since often a character s actions in a story make sense only in terms of a metagoal and the character s plan for pursuing it, recognition of metaplans is essential for story understanding. In the area of language understanding, Litman and Allen[LA87] introduced the notion of discourse metaplans to capture how a speaker might extend, 7 continue, or modify the plan being pursued during a dialogue. As with Wilensky s metaplans, Litman and Allen s metaplans might be termed problem solving plans since they reflected an agent s plan construction ....

Diane Litman and James Allen. A Plan Recognition Model for Subdialogues in Conversation. Cognitive Science, 11:163--200, 1987.

....in response to the user s input in U n ; and (3) domain knowledge, including expected kinds of turns that the user might have produced at this point. The system must first determine what speech act the user is proposing. Many approaches to dialog systems depend on identifying speech acts (e.g. Litman and Allen 1987; Pollack 1990; McRoy and Hirst 1995; Heeman and Hirst 1995; Traum and Hinkelman 1992) In our prototype, the mapping is straightforward; speech acts are limited to the conversation level tasks defined by the four button interface and domain level ones consisting of queries and responses to ....

Litman, D. J., and Allen, J. F. 1987. A Plan Recognition Model for Subdialogues in Conversation. Cognitive Science, 11:163-200.

.... give turn, clarify, and confirm mutual, to explain issues such as turn taking, negotiation of reference, and confirmation of the mutuality of knowledge in mixed initiative dialogue interaction (Novick, 1988) In addition, Kitano and VanEss Dykema extended Litman and Allen s plan recognition model (Litman and Allen, 1987) to explicitly track the conversational initiative based on the domain and discourse plans behind the utterances (Kitano and Van Ess Dykema, 1991) Second, some researchers have investigated the causes of initiative shifts in mixed initiative dialogue interaction and their effect on the structure ....

....utterances based on its model of initiatives. An agent is said to have the task initiative if she is directing how the agents task should be accomplished, i.e. if her utterances directly propose actions that she believes the agent(s) should perform. The utterances may propose domain actions (Litman and Allen, 1987) that directly contribute to achieving the agents goal, such as Why don t we couple engine E2 to the boxcar that s at Elmira, and send it to Corning. 2 On the other hand, the utterances may 2 The majority of the examples in this paper are taken from (Gross et al. 1993) user165.tex; ....

Litman, D. and J. Allen: 1987, `A Plan Recognition Model for Subdialogues in Conversation'. Cognitive Science 11, 163--200.

.... some of which gave fundamental formal accounts of the knowledge which it is based on (Cohen Levesque, 1990; Cohen Perrault, 1979) while others had a more computational bias (Carberry, 1988) More recently domain plans have been complemented with higher levels plans called discourse plans (Litman Allen, 1987) and problem solving plans (Lambert, 1993) While Litman and Allen s discourse plans dealt both with communication strategies and problem solving activities, Lambert separates the discourse level in two parts: in her framework, communicating strategies are represented in the communicative level, ....

Litman, D. & Allen, J. (1987). A plan recognition model for subdialogues in conversation. Cognitive Science, 11 (pp. 163--200).

....is a mutual goal of the interactants [10] Incoherent turns are not always due to misinterpretations: also topic shifts and breakdowns in cooperation should be considered. Currently, we don t model topic shifts due to the initiation of new dialogues; however, as pointed out by many researchers [11, 17, 18], focus and topic shifts are usually marked by the presence of cue words. On the contrary, since we model cooperative dialogues, we exclude the hypothesis that a breakdown in communication can occur. 2 Background Schegloff [24, 25] has analized misunderstandings with respect to the sequences of ....

D. Litman and J. Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200, 1987.

....processes must be coordi Plan chaining can also be done ia effects and prerequisites. To keep the example in the next section simple. plans have been nated. 5 An algorithm for coordinating the recognition of domain and discourse plans from a single utterance has been presented in Litman and Allen [9,11]. In brief, the plan recognizer recognizes a discourse plan from every utterance. then use a process of constraint satisfaction to initiate recognition of the domain and any other discourse plans related to the utterance. Furthermore, to record and monitor execution of the discourse and domain ....

....incorporation of topic relationships into a plan based framework can also be seen as an extension of work in plan recognition. For example, Sidner [21,24] analyzed debuggings (as in the dialogue above) in terms of multiple plans underlying a single utterance. As discussed fully in Litman and Allen [11], the representation and recognition of discourse plans is a systemization and generalization of this approach. Use of even a small set of discourse plans enables the principled understanding of previously problematic classes of dialogues in several task oriented domains. Ultimately the generality ....

D.J. Litman and J. F. Allen. A Plan Recognition Model for Subdialogues in Conversation. Cognitive Science. , to appear. , Also University of Rochester Tech. Rep. 141, November 1984.

....all work on the inverse problem of plan recognition has focused on specific kinds of recognition in specific domains. This includes work on story understanding [Bruce 1981, Schank 1975, Wilensky 1983] psychological modelling [Schmidt 1978] natural language pragmatics [Allen 1983, Carberry 1983, Litman 1987, Grosz Sidner 1987] and intelligent computer system interfaces [Genesereth 1979, Huff Lesser 1982, Goodman Litman 1990] In each case, the recognizer is given an impoverished and fragmented description of the actions performed by one or more agents and expected to infer a rich and highly ....

Litman, Diane & James Allen (1987) A Plan Recognition Model for Subdialogues in Conversation, Cognitive Science, vol 11, pp. 163--200.

No context found.

Diane Litman and James Allen, "A Plan Recognition Model for Subdialogues in Conversation," Cognitive Science, 11, 1987.

....[ Heinsohn et al. 1992 ] focuses on the representation of complex state descriptions, while PROTODL [ Borgida, 1992 ] reconstructs CLASP using natural semantics. While there have been many approaches to plan recognition, e.g. Allen and Perrault, 1980, Carberry, 1990, Cohen and Levesque, 1990, Litman and Allen, 1987, Pollack, 1990, Sidner, 1985 ] our work is most closely related to that of Kautz [ Kautz, 1991 ] Our plan recognition technique, like Kautz s, is deductive, and incorporates the use of a plan abstraction taxonomy (as well as the traditional hierarchy decomposing plans into constituent ....

D. J. Litman and J. F. Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200, 1987.

No context found.

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11:163--200, 1987.

No context found.

Diane Litman and James Allen. A Plan Recognition Model for Subdialogues in Conversation. Cognitive Science, 11:163--200, 1987.

No context found.

Litman, D.J. and Allen, J.F. "A Plan Recognition Model for Subdialogues in Conversation". Cognitive Science 11 (1987), 163 - 200.

No context found.

Diane Litman and James Allen. A plan recognition model for subdialogues in conversation. Cognitive Science, 11(1), 1987.

No context found.

Diane J. Litman and James F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11:163--200, 1987.

No context found.

Diane J. Litman and James F. Allen, \A Plan Recognition Model for Subdialogues in Conversations," Cognitive Science, 11(2):163-200, 1987.

No context found.

Litman D. J., Allen J. A Plan Recognition Model for Subdialogue in Conversations. Cognitive Science 11, p. 163-200, 1987.

No context found.

Litman D. J., Allen J. A Plan Recognition Mo- del for Subdialogue in Conversations. Cognitive Science tt, p. 163-200, 1987.

No context found.

Litman, D. & Allen, J. 1987. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163--200.

No context found.

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163--200, 1987.

No context found.

Diane J. Litman and James F. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, 11(2):163--200, AprilJune 1987.

No context found.

Diane J. Littman and James F. Allen. 1987. A plan recognition model for subdialogues in conversations. Cognitive Science, 11:163--200.

No context found.

D. Litman and J. Allen. A plan recognition model for subdialogues in conversations. Cognitive Science, (11):163--200, 1987.

First 50 documents  Next 50

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