James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, Toronto, Ontario, Canada, 1979.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....They showed [CPA82] that, in question answering systems, users expected the system to recognize their unstated goals in order to provide more helpful responses to questions. Cohen [Coh78, CP79] concentrated on using plan synthesis together with speech acts for natural language generation. Allen [All79, AP80, All83] on the other hand, used plan recognition of speech acts for natural language understanding. We will concentrate here only on Allen s work. Allen studied transcripts of actual interactions at an information booth in a Toronto train station. A typical exchange was something like ....

James F. Allen. A Plan-based Approach to Speech Act Recognition. PhD thesis, University of Toronto, 1979. also Technical Report 131/79.

....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 ....

....intentions that are attributed to the participants, such as the intention that the participants follow through with the subactions that are part of plans for actions in the DM. 349 cilitates recognition of changing beliefs as the dialogue progresses. Allen s representation of an Inform speech act [1] assumed that a listener adopted the communicated proposition. Clearly, listeners do not adopt everything they are told (e.g. IS2 indicates that IS does not immediately accept that Dr. Smith is teaching CIS360) Perrault [6] assumed that a listener adopted the com municated proposition unless ....

James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, Toronto, Ontario, Canaxla, 1979.

....people often use. Our current research [25, 26] views most dialogues as being cooperative and goal directed. i,e. a speaker and listener work together to achieve a common goal. The interpretation of an utterance Involves Identifying the underlying plan or goal that the utterance reflects [5, 1, 23]. This plan, however, is rarely, If ever. obvious at the surface sentence level. A central Issue In the interpretation of utterances is the transformation of sequences of imprecise, illdevised or complex utterances into well secHled plans that might be carried out by dialogue participants. ....

....past experience or knowledge doesn t contain the information the speaker assumes it does or isn t there. then trouble occurs. Thus. one more way referent confusion can occur Is by describing an object using a poor analogy, An analogy used to describe an object might not be specific 4Oroez [14, 1] maul4 demrib this oeo difference tQe# Dlone willie Relchmen [20, 21] would soy that the COmluueJcativo 9o4le differed. enough confusing the listener because several pieces might conform to the analogy or, in fact, none at all appear to fit because discovering a mapping between the ....

Allen, James F. A Plan-Based Approach to Speech Act Recognition. Ph.D. Th.. University of Toronto, 1979,

....for certain regularities that are observable in cooperative responses to questions. The PI model described here has been implemented in SPIRIT, a small demonstration system that answers questions about the domain of computer mail. More Allen s article 121 summarizes his dissertation research [1]. 2O7 extensive discussion of both the PI model and SPIRIT can be found in my dissertation [14] PLANS AS MENTAL PHENOMENA We can distinguish between two views of plans. As Bratman [5, page 271] has observed, there is an ambiguity in speaking of an agent s plan: On the one hand, this] could ....

James F. Allen. A Plan Based Approach to Speech Act Recognition. Technical Report TR 121/79, University of Toronto, 1979.

....speech act. Interpretation and repair attempt to retrace this selection process abductively when a hearer attempts to interpret an observed utterance, he tries to identify the goals, expectations, or misunderstandings that might have led the to produce it. Previous plan based ap proaches [Allen, 1979; Allen, 1983; Litman, 1985; Carberry, 1985] have had difficulty constraining this inference from only a germ of content, potentially a tremendous number of goals could be inferred. A key assumption of our approach, which follows from in sights provided by Conversation Analysis [Garfinkel, ....

James F. Allen. A Plan-Based Ap- proach to Speech Act Recognition. PhD thesis, Department of Computer Science, University of Toronto, Toronto, Canada, 1979. Published as University of Toronto, Department of Computer Science Technical Report No. 131.

....They showed [CPA82] that, in question answering systems, users expected the system to recognize their unstated goals in order to provide more helpful responses to questions. Cohen [Coh78, CP79] concentrated on using plan synthesis together with speech acts for natural language generation. Allen [All79, AP80, All83] on the other hand, used plan recognition of speech acts for natural language understanding. We will concentrate here only on Allen s work. Allen studied transcripts of actual interactions at an information booth in a Toronto train station. A typical exchange was something like ....

James F. Allen. A Plan-based Approach to Speech Act Recognition. PhD thesis, University of Toronto, 1979. also Technical Report 131/79.

....answering systems, users expected the system to recognize their unstated goals in order to provide more helpful responses to questions ( Cohen et al. 1982] Cohen ( Cohen, 1978; Cohen and Perrault, 1979] concentrated on using plan synthesis together with speech acts for content planning. Allen ( Allen, 1979; Allen and Perrault, 1980; Allen, 1983] on the other hand, used plan recognition and speech act theory for intention recognition. We concentrate here only on Allen s work. Allen studied transcripts of actual interactions at an information booth in a Toronto train station. A typical exchange ....

James F. Allen, "A Plan-Based Approach to Speech Act Recognition," Technical Report 131/79, University of Toronto, 1979, PhD thesis.

....requested was not appropriate to his goal. Conversations such as this one, in which the beliefs of the inferring agent differ significantly from the beliefs of the actor whose plan she is inferring, provide a serious challenge to most existing AI systems for plan inference in communication (e.g. [1, 7, 17, 21]) To see why, it is instructive to consider briefly how these systems work. Each of them has an operator library, which encodes a set of recipes for action. These operators are a direct outgrowth of the representations first developed in the STRIPS system [10] and later expanded in the NOAH ....

....the importance of plans as mental attitudes; after all, inferring another agent s plan means figuring out what actions he has in mind. Consider Allen s model, which was one of the earliest accounts of plan inference in conversation and inspired much of the subsequent work in the field [1, 2]. Allen writes AW(P) where P is some proposition, to express the fact that A has a plan to achieve P; AW(ACT) where ACT names some action, expresses the fact that A has a plan to perform ACT. A typical plan inference rule, then, is expressed as SBAW(P) SBAW(ACT) if P is a precondition of ....

James F. Allen. A Plan Based Approach to Speech Act Recognition. Technical Report TR 121/79, University of Toronto, 1979.

....Question, and Tell. If the user s sentence includes unspecified or unknown word, PAU access to Context Base component to figure out the meaning of the word according to the history of conversation. Goal Analyzer takes care of extracting user s goal from his utterance. It uses speech act analysis [1][11] to infer the intention of user. During goal analysis, information stored in User Modeler is referred to specify user s goal according to his type, skill, and knowledge. Also Goal Analyzer accesses to the history information in Context Base to specify the user s knowledge in the current state. ....

Allen,J.F., "A Plan-Based Approach to Speech Act Recognition," Ph.D diss., Dept. of Computer Science, Univ. of Toronto, 1979.

....realized examples of real time, goal oriented interactions between humans and computers. Yet in spite of 30 years of research on algorithms for dialogue management in task oriented dialogue systems, Carbonell, 1971; Winograd, 1972; Simmons Slocum, 1975; Bruce, 1975; Power, 1974; Walker, 1978; Allen, 1979; Cohen, 1978; Pollack, Hirschberg, Webber, 1982; Grosz, 1983; Woods, 1984; Finin, Joshi, Webber, 1986; Carberry, 1989; Moore Paris, 1989; Smith Hipp, 1994; Kamm, 1995) inter alia, the design of the dialogue manager in real time, implemented systems is still more of an art than a science ....

Allen, J. F. (1979). A Plan-Based Approach to Speech Act Recognition. Tech. rep., University of Toronto.

.... for obtaining information, and so she is controlling the conversation (see Walker and Whittaker, 1990) Note that the clerk might even infer the passenger s plan, but he does this in order to provide additional context for her question, or to be able to anticipate any obstacles in her plan (Allen, 1979). 1 So, there are different ways that agents can interact with respect to building a plan. In the case of referring expressions, the agents are mutually responsible for achieving the goal. We feel that this allows the agents to interact such that neither agent assumes control of the dialogue, ....

Allen, J. F. (1979). A plan-based approach to speech act recognition. Doctoral dissertation, Technical Report 131, Department of Computer Science, University of Toronto.

....However, plan recognition techniques ( Carberry, 1990] Ardissono et al. 1998] can play an important role in helping agents to infer what their partners are doing and therefore improving the cooperation of the group. Moreover, plan recognition is independently motivated by communication needs ([Allen, 1979]) 3 The deliberative agent In [Ardissono and Boella, 1998] we describe the agent architecture that we assume underlies this work. Here, we just say that the knowledge about how to act is stored in three libraries of actions. For each action, its preconditions, its constraints and its effects ....

Allen, J. (1979). A plan-based approach to speech act recognition. PhD thesis, University of Toronto.

....knowledge intensive processes, such as recognizing doubt or clarification sub dialogues and robust ellipsis resolution. 3 Plan inference based discourse processing Our plan based discourse processor follows previous work of using a plan inference model for understanding discourse utterances [2, 27, 7, 22]. Plan based approaches are based on Austin s [3] and Searl s [40] notionof language as a series of actions, and Grice s [13] and Searle s description of language as goal oriented behavior. Specifically, we developed our discourse processor following Lambert s work [22, 23] on understanding ....

....when performed under certain conditions (i.e. if certain beliefs and preconditions hold) bring about certain effects or goals. These subplans are called plan operators. Discourse plan operators represent knowledge about how to achieve discourse goals. Our plan operators are similar to those of [2, 27, 7, 22]. Each plan operator consists of a header, a type, a (possibly empty) set of preconditions, a (possibly empty) set of constraints on the variables, a (possibly empty) set of applicability conditions, a (possibly empty) set of actions that form a body, a set of effects, and a goal. Figure 3 shows ....

J. F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, School of Computer Science, 1979.

....and one non autonomous agent, independent of the information distribution, as long as the agents are resource bounded. 1 Introduction The view that communication is a type of action has provided a basis for research in natural language processing for many years [ Grice, 1957; Austin, 1965; Allen, 1979; Cohen, 1978; Litman, 1985 ] However, models of taskoriented dialogic interaction fail to fully exploit the language as action perspective because there is no deep understanding of the interaction between the definition of the task, the autonomy of the agents doing the task, and efficient ....

James F. Allen. A plan-based approach to speech act recognition. Technical report, University of Toronto, 1979.

....formalism [Cohen Perrault 79] This work showed how to construct a plan out of speech acts to achieve goals such as requesting or imparting information. Allen, Cohen, and Perrault also described algorithms for inferring the goals of a speaker given the speech acts the speaker performs [Allen 79, Perrault Allen 80, Allen 83] One motivation of this work was to create a question answering system that would supply more information than strictly required by the question [Allen Perrault 80, Cohen et al. 81] For example, consider the following dialogue taken from transcripts collected at an information booth ....

C. Perrault and J. Allen. A plan-based approach to speech act recognition. American Journal of Computational Linguistics, 6(3-4):167-- 182, 1980.

....formalism [Cohen Perrault 79] This work showed how to construct a plan out of speech acts to achieve goals such as requesting or imparting information. Allen, Cohen, and Perrault also described algorithms for inferring the goals of a speaker given the speech acts the speaker performs [Allen 79, Perrault Allen 80, Allen 83] One motivation of this work was to create a question answering system that would supply more information than strictly required by the question [Allen Perrault 80, Cohen et al. 81] For example, consider the following dialogue taken from transcripts collected at ....

J. Allen. A plan-based approach to speech act recognition. PhD dissertation, Department of Computer Science, University of Toronto, 1979.

....though, if one considers that a user modeling shell system must be domain independent while heuristics for acquiring primary assumptions concerning the user are mostly domain dependent. For example, if the user asks the system the following question: When is the next train to Montreal [Allen, 1979] then one would most likely assume that the user wants to go to Montreal on the next train. But this is only true in travel domains. The assumption is no longer valid in rail shipping domains (for example in [Allen and Schubert, 1993] where it is more likely that the user may just want to ship a ....

J. F. Allen. A Plan-Based Approach to Speech Act Recognition. Technical Report 131/79, Dept. of Computer Science, University of Toronto, 1979.

....say either unmotivated or obscure or both. Once we reach section 4, we treat the two systems together, showing how paths map to Bayesian networks, and how path calculations yield an upper bound on the joint probability of the nodes in the Bayesian network. 2 Previous Work Allen proposed a scheme (Allen [1979]) to do plan recognition in the context of cooperative dialogue. The search for candidate plans was essentially carried out using a forward chaining search up the plan hierarchy, unifying proposed plan alternatives with the system s expectations and current plan information. He used a heuristic ....

Allen, James F. [1979], "A Plan-Based Approach to Speech Act Recognition," University of Toronto, Ph.D. Thesis.

....(action,hearer) Figure 2: Definition of the REQUEST ACT plan operator from Litman and Allen, 1987 perform. These acts may be either physical movements or linguistic behavior. We focus exclusively on linguistic behavior. Our work draws from two theoretical bases: computational work on SPEECH ACTS [Allen, 1979, Cohen, 1978, Litman, 1985] and social anthropology and linguistics research on social interaction [Goffman, 1983, Brown and Levinson, 1987] In section 2, we introduce the components of speech act theory that we draw on, then in section 3 we discuss in detail Brown and Levinson s theory of ....

....if the speaker is successful. Initial computational work proposed that speech acts should be implemented in a standard AI planning system as plan operators that include the act s DECOMPOSITION, PRECONDITIONS and EFFECTS, thereby enabling computer agents to plan utterances as well as physical acts [Allen, 1979, Cohen, 1978, Litman, 1985] While many different inventories of speech acts are possible, our taxonomy consists of the initiating acts of INFORM, OFFER and two types of REQUEST: REQUEST INFO and REQUEST ACT. We also use three types each of response speech acts for acceptance and rejection, ....

James F. Allen. A plan-based approach to speech act recognition. Technical report, University of Toronto, 1979.

.... LSI are important for any domain in which agents speak, such as characters for interactive drama systems, multimodal interface agents and spoken dialogue agents(CPB 94; LB95; RWS 94; MDBP94; HRB94; Kam95) Our work on LSI draws from two theoretical bases: computational work on speech acts(All79; Coh78; header: request act(speaker, hearer, action) precondition: want(speaker,action) cando(hearer,action) decomposition 1: surface request(speaker,hearer,action) decomposition 2: surface request(speaker,hearer, informif (hearer,speaker, cando(hearer,action) decomposition 3: ....

.... Earlier computational work proposed that speech acts should be implemented in a standard AI planning system as plan operators that include the act s decomposition, preconditions and effects, thereby enabling computer agents to plan utterances in the same way that they plan physical acts(All79; Coh78; Lit85) An example plan based representation of a request act (for example, Laszlo s request in 1a) based on Litman and Allen s work, is given in Figure 2(LA90) A critical basis of our improvisation algorithms is speech act theory s distinction between the underlying intention of a ....

James F. Allen. A Plan-Based Approach to Speech Act Recognition. Technical report, University of Toronto, 1979.

....this, there was a great deal of research in AI dealing with planning (for early, foundational work in this area, see Newell Simon, 1972; Sacerdoti, 1977; Fikes Nilsson, 1971) By making use of this, some systems attempted to directly understand text by identifying the plans of the characters. Allen (1979; 1983) and Wilensky (1981) were among the first to attempt this. Others included Carberry (1988) and Sidner (1985) Plan recognition is a powerful technique, particularly when the reader is able to understand the interactions of characters and their plans, rather than understanding a single ....

Allen, J. F. (1979). A plan-based approach to speech act recognition. Technical Report 131, University of Toronto.

....work admits a serious flaw. Although the preconditions of these operators are formulated in terms of the understanding of the planning agent, the post conditions or effects of these operators do not update the understanding of the planning agent, but of the agent at whom the action is directed [1]. No agent can ever actually know with any certainty anything about the effects of an action, whether communicative or otherwise. It is only through an understanding of the target agent and through observing the future behaviour of that agent, that the agent can discover the actual effects of the ....

J. Allen, `A plan-based approach to speech act recognition', Technical Report 131, Department of Computer Science, University of Toronto, (1979).

....yet know, even in principle, how to carry out either of these tasks, the implications for language technology remain speculative. Attempts to develop commonalities between generation and interpretation have not been very encouraging. For instance, James Allen s early work on plan recognition in Allen (1979) obtained some plan recognition rules by reversing discourse plan rules. This induced a simple relationship between some of the planning rules and rules of interpretation. But the technique does not seem to hold up: in the later, more thoroughly formalized version of Allen s plan recognition ....

Allen, J. F. 1979. A Plan-Based Approach to Speech Act Recognition. Ph.D. Dissertation, University of Toronto, Toronto, Ontario, Canada.

....engineering skill level in guessing whether the user knows the tool product. The higher the user s skill level, the more likely the user knows the tool product. The user s skill level and security level is used by MC to understand certain indirect speech acts (Searle 1975) Following the lead of (Allen 1979; Allen Perrault 1980) the indirect speech act is analyzed based on the user s plans and goals. If the user is asking whether MC or the user can do X, then the user may be asking whether MC or the user has the ability or permission to do X (the direct speech act) or the user may be asking MC to ....

Allen, J. F. 1979. A Plan-Based Approach to Speech Act Recognition. Ph.D. diss., Dept. of Computer Science, Univ. of Toronto. Also available as Technical Report No. 131, Univ. of Toronto.

.... agents, discovering limitations in what agents can know about each other [36] Research on dialogue comprehension in natural language understanding is also relevant to CDPS research because both research areas must reason about multiple agents with distinct and possibly contradictory mental states [1, 9]. Mental states include not only facts or knowledge but also beliefs and goals. An agent must interpret messages from other agents, including what the messages imply about the agents mental states, and must generate messages to alter the mental states of other agents, taking into account the ....

James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, February 1979. (Also published as Technical Report 131/79, Department of Computer Science, University of Toronto, Toronto, Canada, February 1979.).

....to a discourse plan, and determine how the discourse plan operates on an existing or new task plan. Just as with dialogue grammars, multi level plan recognizers can be used to generate expectations for future actions and utterances, thereby assisting the interpretation of utterance fragments (Allen, 1979; Allen Perrault, 1980; Carberry, 1985; Carberry, 1990; Sidner, 1985) and even providing constraints to speech recognizers (Andry, 1992; Yamaoka Iida, 1991; Young, Hauptmann, et al. 1989) Complexity of Inference: The processes of plan recognition and planning are combinatorially ....

Allen, J. F. (1979). A plan-based approach to speech act recognition. Technical Report 131, Department of Computer Science, University of Toronto, Toronto, Canada.

....chosen speech act. Interpretation and repair attempt to retrace this selection process abductively when a hearer attempts to interpret an observed utterance, he tries to identify the goals, expectations, or misunderstandings that might have led the to produce it. Previous plan based approaches [ Allen, 1979; Allen, 1983; Litman, 1985; Carberry, 1985 ] have had difficulty constraining this inference from only a germ of content, potentially a tremendous number of goals could be inferred. A key assumption of our approach, which follows from insights provided by Conversation Analysis [ Garfinkel, ....

James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, Department of Computer Science, University of Toronto, Toronto, Canada, 1979. Published as University of Toronto, Department of Computer Science Technical Report No. 131.

.... that all plan recognition is inherently a kind of abductive problem independent of the actual plan recognition model (see [May92] The traditional approach to plan recognition, found in seminal works of Wilensky ( and Allen ( is to chain together a sequence of abductive inferences (cf. All79] Wil78] Using the advantages of a formal logic based theory like clear semantics our approach is based on the modal temporal logic LLP (cf. section 3) This logic has proved to be an effective means of plan recognition as well as of planning (see [BBD 93] so that one uniform ....

J.F. Allen. A plan-based approach to speech act recognition. Technical Report (Doctoral Dissertation) 131/79, University of Toronto, Department of Computer Science, 1979.

....considerable work has been done in the area of planning, very few planning systems have addressed the problem of how to detect appropriate goals for planning. In almost all planning systems, the high level goals are provided by the human operators of the planners. An exception is described by [Allen79], whose system simulated a train station ticket agent. It detected goals based on an analysis of obstacles to a user s plans. By addressing these obstacles, the system could volunteer information that the user would need to achieve the user s plan. This approach addresses only a fraction of the ....

Allen, J. F., 1979. A Plan-Based Approach to Speech Act Recognition. Ph.D. thesis, Department of Computer Science, University of Toronto. Also available as Technical Report 131, University of Toronto.

....Discourse Several researchers have been motivated by the role of plan reasoning in discourse, and much of this is based on the same motivations as I have presented for mixed initiative planning. The connection between planning and discourse was initially noted in work by Cohen [1978; 1979] and Allen [1979; 1980; 1983b] in applying AI planning techniques to the theory of speech acts developed by Austin [1962] and Searle [1969] They noted that if speech acts (i.e. things that can be done by speaking) are represented as planning operators with preconditions, effects, and so on, then it is possible ....

James F. Allen, A plan-based approach to speech act recognition, PhD thesis, Department of Computer Science, University of Toronto, Toronto, Ont., 1979.

No context found.

James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, Toronto, Ontario, Canada, 1979.

No context found.

James F. Allen, \A Plan-Based Approach to Speech Act Recognition," Technical Report 131/79, University of Toronto, 1979, PhD thesis.

No context found.

James F. Allen. A Plan-Based Ap- proach to Speech Act Recognition. PhD thesis, University of Toronto, Toronto, Ontario, Canada, 1979.

No context found.

Allen, J. A plan-based approach to speech act recognition, Technical Report No. 131179 (February 1979), Department of Computer Science, University of Toronto, Toronto, Canada.

No context found.

James F. Allen. 1979. A plan-based approach to speech act recognition. Technical report, University of Toronto.

No context found.

J.F. Allen. A plan-based approach to speech act recognition. Technical Report 131, Department of Computer Science, University of Toronto, Toronto, Canada, January 1979.

No context found.

James F. Allen. A Plan-Based Approach to Speech Act Recognition. PhD thesis, University of Toronto, Toronto, Ontario, Canada, 1979.

No context found.

James F. Allen. 1979. A Plan-Based Approach to Speech Act Recognition. Ph.D. thesis, University of Toronto, Toronto, Ontario, Canada.

No context found.

J.F. Allen (1979) A Plan based approach to Speech Act Recognition. PhD Thesis University of Toronto.

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