A tripartite plan-based model of dialogue

Lambert, Lynn; Carberry, Sandra

doi:10.3115/981344.981351

Cited by 77 publications

(64 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such an ambiguity can be solved by considering the concept sequence of utterance (3). If only the speech act of utterance (2) is considered, the speech act of utterance (3) may be inform.…”

Section: Failure Analysismentioning

confidence: 99%

“…Previous studies on the determination of a system's domain action have been based on dialogue models, such as finite-state models, frame-based models [12], and plan-based models [3,4]. A finite-state model consists of a set of nodes representing dialogue states and a set of arcs between the nodes.…”

Section: Related Workmentioning

confidence: 99%

“…Previous studies on the determination of users' domain actions are divided into the following two groups: one is the use of handcrafted rules such as recipes for plan inference and domain specific knowledge [2][3][4], and the other is the use of machine learning techniques based on a large annotated corpus [5][6][7][8][9][10][11]. The rule-based methods have shown good performances in small dialogue domains.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues

Lee

Kim

Seo

2013

Journal of Information Processing Systems

View full text Add to dashboard Cite

Abstract-A speaker's intentions can be represented by domain actions (domainindependent speech act and domain-dependent concept sequence pairs). Therefore, it is essential that domain actions be determined when implementing dialogue systems because a dialogue system should determine users' intentions from their utterances and should create counterpart intentions to the users' intentions. In this paper, a neural network model is proposed for classifying a user's domain actions and planning a system's domain actions. An integrated neural network model is proposed for simultaneously determining user and system domain actions using the same framework. The proposed model performed better than previous non-integrated models in an experiment using a goal-oriented dialogue corpus. This result shows that the proposed integration method contributes to improving domain action determination performance.

show abstract

“…Such an ambiguity can be solved by considering the concept sequence of utterance (3). If only the speech act of utterance (2) is considered, the speech act of utterance (3) may be inform.…”

Section: Failure Analysismentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues

Lee

Kim

Seo

2013

Journal of Information Processing Systems

View full text Add to dashboard Cite

show abstract

“…A scheme is explained with which the system is able to take task goals, text goals and text structure into account for generating text. (Lambert and Carberry, 1991) discusses another plan-based model of dialogue, which has three plan levels: domain level, problem solving level, and discourse level. (Lambert and Carberry, 1992) continues on the previous model, which is extended for modelling conflicting beliefs and negotiating about such conflicts, thus enabling negotiation subdialogues.…”

Section: Modelling Of Dialogue Structurementioning

confidence: 99%

Overview of Current Research

López-de-Silanes¹

2007

Social Skills and Autistic Spectrum Disorders

View full text Add to dashboard Cite

This text is an overview of literature relevant to the development and modelling of interactive systems. It is the most comprehensive part of the documentation I made during the literature research stage of my PhD project, which should result in a modelling framework for interactive systems. More precisely, the scope of this project is natural language, multimodal, and virtual reality systems, and ways of modelling the dynamics of interaction of such systems for the purpose of aiding system development. The topics addressed in this text naturally include existing systems and modelling techniques, but theoretical frameworks and methodological issues are also addressed. Short introductions are given to cognitive psychology, semiotics, communication models, and HCI. Systems and strategies are reviewed, covering the topics multimodality, redundancy and confirmation, and ways of modelling dialogue and task structure. Methodological issues are reviewed, in particular some methodologies, and strategies for design/implementation and analysis/evaluation. Finally, some conclusions are given, as well as an indication of the directions of my future research.1

show abstract

“…Cohen (1992) and Jacob (1995), among others, have explored discourserelated extensions to direct manipulation that incorporate anaphora and make previous context directly available. However, most work on applying human discourse principles to human-computer interaction, e.g., (Lambert and Carberry, 1991;Yanklovich, 1994), have assumed that natural language understanding will be applied to the user's utterances In Moore et al's work (Lemaire and Moore, 1994;Moore and Swartout, 1990), which focuses on explanation dialogues, users are presented with a full textual history of their interaction with the system, from which they may select any phrase as the context for a further query. Unlike our approach, Moore's history display has no explicit structure other than the alternation of user and system utterances.…”

Section: Comparison With Other Workmentioning

confidence: 99%

COLLAGEN: A Collaboration Manager for Software Interface Agents

Rich¹,

Sidner²

1998

Computational Models of Mixed-Initiative Interaction

103

View full text Add to dashboard Cite

We have implemented an application-independent collaboration manager, called Collagen, based on the SharedPlan theory of discourse, and used it to build a software interface agent for a simple air travel application. The software agent provides intelligent, mixed initiative assistance without requiring natural language understanding. A key benefit of the collaboration manager is the automatic construction of an interaction history which is hierarchically structured according to the userś and agentś goals and intentions. User Modeling and User-Adapted Interaction, Special Issue on Computational Models for Mixed Initiative InteractionThis work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. AbstractWe have implemented an application-independent collaboration manager, called Collagen, based on the SharedPlan theory of discourse, and used it to build a software interface agent for a simple air travel application. The software agent provides intelligent, mixed initiative assistance without requiring natural language understanding. A key benefit of the collaboration manager is the automatic construction of an interaction history which is hierarchically structured according to the user's and agent's goals and intentions. To appear in User Modeling and User-Adapted Interaction, Special Issue on Computational Models for Mixed Initiative Interaction.This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Information Technology Center America; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Information Technology Center America. All rights reserved. Abstract. We have implemented an application-independent collaboration manager, called Collagen, based on the SharedPlan theory of discourse, and used it to build a software interface agent for a simple air travel application. The software agent provides intelligent, mixed initiative assistance without requiring natural language understanding. A key benefit of the co...

show abstract

A tripartite plan-based model of dialogue

Cited by 77 publications

References 12 publications

An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues

An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues

Overview of Current Research

COLLAGEN: A Collaboration Manager for Software Interface Agents

Contact Info

Product

Resources

About