• Corpus ID: 195767665

Enabling Dialogue Management with Dynamically Created Dialogue Actions

@article{Miehle2019EnablingDM,
  title={Enabling Dialogue Management with Dynamically Created Dialogue Actions},
  author={Juliana Miehle and Louisa Pragst and Wolfgang Minker and Stefan Ultes},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.00684}
}
In order to take up the challenge of realising user-adaptive system behaviour, we present an extension for the existing OwlSpeak Dialogue Manager which enables the handling of dynamically created dialogue actions. This leads to an increase in flexibility which can be used for adaptation tasks. After the implementation of the modifications and the integration of the Dialogue Manager into a full Spoken Dialogue System, an evaluation of the system has been carried out. The results indicate that… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 14 REFERENCES
Towards an Ontology-Driven Adaptive Dialogue Framework
TLDR
The principles and technologies that underpin the development of an adaptive dialogue manager framework that can handle dynamically created user and system actions, while still enabling the agent to adapt its actions to various and possibly changing contexts are described.
OwlSpeak - adaptive spoken dialogue within Intelligent Environments
TLDR
The OwlSpeak dialogue manager that enables adaptive spoken dialogue within Intelligent Environments by facilitating an ontology-based model to define both dialogue domain and state during the ongoing dialogue is described and VoiceXML dialogue snippets are generated.
Quality-adaptive Spoken Dialogue Initiative Selection And Implications On Reward Modelling
TLDR
This work presents an evaluation of a quality- Adaptive strategy with a user simulator adapting the dialogue initiative dynamically during the ongoing interaction and shows that it outperforms conventional non-adaptive strategies and a random strategy.
Managing adaptive spoken dialogue for Intelligent Environments
TLDR
HIS-OwlSpeak is presented, a model-driven dialogue manager for Intelligent Environments that meets the challenges arising from engineering IEs by providing a unified platform comprising adaptivity to a variety of internal and external factors.
Exploring the Applicability of Elaborateness and Indirectness in Dialogue Management
TLDR
It is shown that elaborateness and indirectness influence the user’s impression of a dialogue and should be incorporated in adaptive dialogue management.
LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data
TLDR
This work focuses on improving the identification, disambiguation and linking of entities occurring in data sources and user input, and expanding the typical information seeking dialogue model (slot filling) to better reflect real-world conversational search scenarios.
KRISTINA: A Knowledge-Based Virtual Conversation Agent
TLDR
An intelligent embodied conversation agent with linguistic, social and emotional competence constructed around an ontology-based knowledge model that allows for flexible reasoning-driven dialogue planning, instead of using predefined dialogue scripts.
Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda
TLDR
RavenClaw is described, a new dialog management framework developed as a successor to the Agenda architecture used in the CMU Communicator, and allows rapid development of dialog management components for spoken dialog systems operating in complex, goal-oriented domains.
Companion-Technology: Towards User- and Situation-Adaptive Functionality of Technical Systems
TLDR
The involved key components of such a system and the way they interact with each other are described and the gained knowledge reflects the context of use and serves as basis for decision-making in the presented adaptive system.
Probabilistic Human-Computer Trust Handling
TLDR
This paper conducts a webbased study testing the effects of different goals of explanations on the components of human-computer trust, and shows how these results can be used in the probabilistic trust handling architecture to augment pre-defined task-oriented dialogs.
...
...