Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems

López-Cózar, Ramón; Callejas, Zoraida; Ábalos, Nieves; Espejo, Gonzalo; Griol, David

doi:10.1007/978-3-642-15760-8_66

Cited by 2 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the recent research, we can find several works dealing with the user-system dialogue where the communication is done through a real human language (Karsenty and Botherel, 2005;Lopez-Cozar et al, 2010;Rapaport, 2003). According to Rapaport (2003), negotiation is the key to understanding: a cognitive agent understands by negotiating with the interlocutor or by hypothesizing the meaning of an unknown word from the context.…”

Section: Related Workmentioning

confidence: 99%

“…Other works propose to use confidence scores to measure the reliability of each word in a recognized sentence (Jiang, 2005). Besides, Lopez-Cozar et al (2010) proposed to implement a frame correction module, independent of the speech recognizer. This module corrects misunderstandings in a sentence, caused by errors in speech recognition, by replacing the incorrect frame with an adequate one.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A situation-based multi-agent architecture for handling misunderstandings in interactions

Pham

Rabah

Estraillier

2015

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

During interactions, system actors may face up misunderstandings when their local states contain inconsistent data about the same fact. Misunderstandings in interactions are likely to reduce interactivity performances (deviation or deadlock) or even affect overall system behavior. In this paper, we characterize misunderstandings in interactions between system actors (that may be human users or system agents) in interactive adaptive systems. To deal with such misunderstandings and ensure state consistency, we present an agent-based architecture and a scenario structuring approach. The system includes several agents devoted to scenario unfolding, plot adaptation and consistency management. Scenario structuring is based on the notion of a situation that is an elementary building block dividing the interactions between systems' actors into contextual scenes. This pattern supports not only scenario execution but consistency management as well. In order to organize and control interactions, the situation contextualizes interactions and activity of the system's actors. It also includes prevention and tolerance agent-based mechanisms to deal with the misunderstandings and their causes. We validate our consistency management mechanisms using Uppaal simulation and provide some experimental results to show the effectiveness of our approach on an online distance learning case study.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A situation-based multi-agent architecture for handling misunderstandings in interactions

Pham

Rabah

Estraillier

2015

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…In the recent research, we can find several works dealing with the user-system dialogue where the communication is done through a real human language [2][3][4][5]. According to Rapaport [4], negotiation is the key to understanding.…”

Section: Recent Workmentioning

confidence: 99%

“…Other works propose to use confidence scores to measure the reliability of each word in a recognized sentence [6]. Besides, Lopez-Cozar proposed to implement a frame correction module, which is independent of speech recognizer [3]. This module corrects misunderstandings in a sentence, caused by the errors in speech recognition, by replacing the incorrect frame with an adequate one.…”

Section: Recent Workmentioning

confidence: 99%

Handling the misunderstanding in interactions: Definition and solution

Pham¹,

Rabah²,

Estraillier³

2011

PsycEXTRA Dataset

View full text Add to dashboard Cite

I n this paper we introduce our explorative work on the concepts and taxonomy of the misunderstanding in interaction and on the architectural mechanism solving this problem in interactive systems. System actors interacting during the software execution may face misunderstandings when the internal data of at least one actor evolve differently from other , after the same sequence of interactions within a common context. We formally define the misunderstandings in interaction and propose an architecture including mechanisms to detect, treat and avoid them. These mechanisms insure the consistency of system s actor data at the end of each interaction sequence in the application scenario.

show abstract

Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems

Cited by 2 publications

References 7 publications

A situation-based multi-agent architecture for handling misunderstandings in interactions

A situation-based multi-agent architecture for handling misunderstandings in interactions

Handling the misunderstanding in interactions: Definition and solution

Contact Info

Product

Resources

About