• Corpus ID: 55317194

Evaluating Combinations of Dialogue Acts for Generation

@inproceedings{Keizer2007EvaluatingCO,
  title={Evaluating Combinations of Dialogue Acts for Generation},
  author={Simon Keizer and Harry Bunt and Tim Paek},
  booktitle={SIGDIAL Conferences},
  year={2007}
}
We will discuss an approach to dialogue act generation that reflects the multidimensionality of communication. Dialogue acts from different dimensions in the taxonomy used are generated in parallel, resulting in a buffer of candidates. The main focus of the paper will be on an additional process of evaluating these candidates, resulting in definitive combinations of dialogue acts to be generated. This evaluation process is required to deal with the interdependencies there still are between… 

Figures from this paper

A Context-Change Semantics for Dialogue Acts

An update semantic for dialogue acts is presented, defined in terms of combinations of ‘elementary update functions’, which allows fine-grained distinctions to be made between related types of dialogue acts, and relations like entailment and exclusion between dialogue acts to be established.

Empirical and theoretical constraints on dialogue act combinations

This paper presents an empirical study and analytical examination of the actual and possible co-occurrence of dialogue acts in dialogue units of various sorts. We formulate semantic and pragmatic

Multidimensional Dialogue Management

An approach to dialogue management that supports the generation of multifunctional utterances based on the multidimensional dialogue act taxonomy and associated context model as developed in Dynamic Interpretation Theory (DIT).

The DIT++ taxanomy for functional dialogue markup

The DIT ++ taxonomy of communicative functions, with some of its background and theoretical motivations, is presented, and its role is indicated in a recently started effort of the ISO organization to develop an international standard for functional dialogue markup.

Interpretation and Generation of Dialogue with Multidimensional Context Models

  • H. Bunt
  • Psychology
    COST 2102 Training School
  • 2010
A 10-dimensional taxonomy of communicative functions has been developed, which has been applied successfully by human annotators and by computer programs in the analysis of spoken and multimodal dialogue and which forms the basis of an ISO standard for dialogue act annotation.

Multifunctionality in dialogue

  • H. Bunt
  • Psychology
    Comput. Speech Lang.
  • 2011

Use of the QuADS Architecture for Multimodal Output Generation

The means by which a system developed with QuADS selects the modalities that it will use to present information to the user is examined, taking into account the availability of a particular modality in a given system configuration, and considering also the user’s preference for particular modalities.

M an us cr ip t Multifunctionality in dialogue

This paper studies the multifunctionality of dialogue utterances, i.e. the phenomenon that utterances in dialogue often have more than one communicative function. It is argued that this phenomenon

The MaDrIgAL project: Multi-Dimensional Interaction Management and Adaptive Learning

The MaDrIgAL project aims to develop multi-dimensional versions of data-driven models for spoken dialogue systems that incorporate a richer set of dialogue acts into the learning process, leading to more natural and socially appropriate dialogues.

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

This paper presents a multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication and using multi-agent reinforcement learning.

A conversation acts model for generating spoken dialogue contributions

Multidimensional Dialogue Management

An approach to dialogue management that supports the generation of multifunctional utterances based on the multidimensional dialogue act taxonomy and associated context model as developed in Dynamic Interpretation Theory (DIT).

An architecture and applications for speech-based accessibility systems

The Jaspis speech application architecture is presented, which introduces a new paradigm for adaptive applications and has been released as open-source software to assist in practical application development and to illustrate how the architecture supports adaptive interaction and accessibility.

Draft of DAMSL Dialog Act Markup in Several Layers

In uencing-addressee-future-action (In uence-on-listener) 2.4.2 Utterance-Tags 4 2.3.4 Committing-speaker- future- action (In Uence- on-spe speaker) .

Dialogue pragmatics and context specification

  • H. Bunt
  • Computer Science
    Abduction, Belief and Context in Dialogue
  • 2000