A rational agent as the kernel of a cooperative spoken dialogue system: Implementing a logical theory of interaction

Bretier, Philippe; Sadek, M. D.

doi:10.1007/bfb0013586

Cited by 49 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The general picture (due historically to [5], see [3] for discussion) is this. An agent desires to have the environment have a certain feature.…”

Section: Planning a Speech Actmentioning

confidence: 98%

“…In KD45, formula 8 is equivalent to formula 6, 3 and formula 9 is equivalent to formula 4. 4 The embedded disjunction in formula 10 expresses a tautology, according to Rule 6.…”

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

“…It might also be noted that (3) implies (6), 5 and also that (3) implies (7). 6 (6) and (7) imply (3). 7 This has various implications.…”

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

“…To decide this, we need to determine whether there is an identifiable speech act that has (6) as a precondition but not (7)…or the reverse. If we decide this is not possible, then (6) and (7) should not count as separate FFs, but rather we should only use (3). If, on the other hand, we find there to be speech acts that have only one of them in their FP-set, then (3) should not count as a separate FF but instead we should allow (6) and (7) to occur separately sometimes, and sometimes together.…”

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

See 3 more Smart Citations

Enumerating the Preconditions of Agent Message Types

Pelletier

Elio

2003

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. Agent communication languages (ACLs) invoke speech act theory and define individual message types by reference to particular combinations of beliefs and desires of the speaker (feasibility preconditions). Even when the mental states are restricted to a small set of nested beliefs, it seems that there might be a very large number of different possible preconditions, and therefore a very large number of different message types. With some constraints on the mental attitude of the speaker, we enumerate the possible belief states that could serve as preconditions for individual message types, and we identify how these states correspond to different possible message types. We then compare these with FIPA's primitive message types. Our approach clarifies the nature of core message types in an ACL, and perhaps settles issues concerning just how many, and what types of, speech acts should be seen as primitive in such languages.

show abstract

“…The general picture (due historically to [5], see [3] for discussion) is this. An agent desires to have the environment have a certain feature.…”

Section: Planning a Speech Actmentioning

confidence: 98%

“…In KD45, formula 8 is equivalent to formula 6, 3 and formula 9 is equivalent to formula 4. 4 The embedded disjunction in formula 10 expresses a tautology, according to Rule 6.…”

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

“…It might also be noted that (3) implies (6), 5 and also that (3) implies (7). 6 (6) and (7) imply (3). 7 This has various implications.…”

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

Section: Further Semantic Restrictions On Fp-setsmentioning

confidence: 99%

See 2 more Smart Citations

Enumerating the Preconditions of Agent Message Types

Pelletier

Elio

2003

Advances in Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…According to Zukerman and Litman [168], very early examples of user modeling in these field are dominated by knowledge-based formalisms and various types of logic aimed at modeling the complex beliefs and intentions of agents [27,46,103,133]. Grosz and Sidner analyzed the discourse structure as composed of the linguistic structure, the intentional structure, and an attentional state [58,65].…”

Section: Modeling the User Intentionmentioning

confidence: 99%

Modeling the user state for context-aware spoken interaction in ambient assisted living

2014

View full text Add to dashboard Cite

Ambient Assisted Living (AAL) systems must provide adapted services easily accessible by a wide variety of users. This can only be possible if the communication between the user and the system is carried out through an interface that is simple, rapid, effective, and robust. Natural language interfaces such as dialog systems fulfil these requisites, as they are based on a spoken conversation that resembles human communication. In this paper, we enhance systems interacting in AAL domains by means of incorporating context-aware conversational agents that consider the external context of the interaction and predict the user's state. The user's state is built on the basis of their emotional state and intention, and it is recognized by means of a module conceived as an intermediate phase between natural language understanding and dialog management in the architecture of the conversational agent. This prediction, carried out for each user turn in the dialog, makes it possible to adapt the system dynamically to the user's needs. We have evaluated our proposal developing a context-aware system adapted to patients suffering from chronic pulmonary diseases, and provide a detailed discussion of the positive influenc of our proposal in the success of the interaction, the information and services provided, as well as the perceived quality.

show abstract