The user model-based summarize and refine approach improves information presentation in spoken dialog systems

Winterboer, Andi; Tietze, Martin I.; Wolters, Maria; Moore, Johanna D.

doi:10.1016/j.csl.2010.04.003

Cited by 5 publications

(3 citation statements)

References 39 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Winterboer et al propose a user-model based summarize and refine approach that improves task success, efficiency, and user satisfaction with dialog systems. 115 Recently, Wang and Swegles propose a technique that employs knowledge about the user's activity to disambiguate their spoken inputs. 108 A Reinforcement Learning algorithm is proposed to acquire the knowledge and apply it for disambiguation.…”

Section: Related Workmentioning

confidence: 99%

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

Griol

Iglesias

Ledezma

et al. 2016

Int. J. Neur. Syst.

View full text Add to dashboard Cite

This paper proposes a statistical framework to develop user-adapted spoken dialog systems. The proposed framework integrates two main models. The first model is used to predict the user's intention during the dialog. The second model uses this prediction and the history of dialog up to the current moment to predict the next system response. This prediction is performed with an ensemble-based classifier trained for each of the tasks considered, so that a better selection of the next system can be attained weighting the outputs of these specialized classifiers. The codification of the information and the definition of data structures to store the data supplied by the user throughout the dialog makes the estimation of the models from the training data and practical domains manageable. We describe our proposal and its application and detailed evaluation in a practical spoken dialog system.

show abstract

Section: Related Workmentioning

confidence: 99%

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

Griol

Iglesias

Ledezma

et al. 2016

Int. J. Neur. Syst.

View full text Add to dashboard Cite

show abstract

“…Most relevant of these works propose the distribution of the results clustered for all the possible query parameters (restrictions), as described in [13] and ( [14]). Other proposals also include the use of a user model and discourse makers (e.g., connective and discourse adverbials) to express differences in a clear succinct and effective way, as in [15]. These strategies could have limitations on web systems, because the amount of information is huge and clustering the set of results could be costly.…”

Section: Introductionmentioning

confidence: 96%

Using domain knowledge for fostering the collaborative ability of a web dialogue system

Gatius

González

2011

2011 7th International Conference on Next Generation Web Services Practices

View full text Add to dashboard Cite

In this paper we describe the use of domain ontologies in a flexible web dialogue system for improving both its adaptability and its collaborative ability. We have developed a multilingual mixed-initiative dialogue system for guiding the user when accessing several types of web services. The use of domain ontologies facilitates the adaptation of the system to new web services as well as the generation of more collaborative responses.

show abstract

“…Can this be repeated in order to carry out a hierarchical search over dynamically computed item categories? This kind of search can be considered as a question-answering game [26]. At each round of the game, the recommended items are dynamically split into K item categories, which are presented to the user who selects the category of the target item.…”

Section: Introductionmentioning

confidence: 99%

Minimal Interaction Search in Recommender Systems

Kveton

Berkovsky

2015

Proceedings of the 20th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

While numerous works study algorithms for predicting item ratings in recommender systems, the area of the userrecommender interaction remains largely under-explored. In this work, we look into user interaction with the recommendation list, aiming to devise a method that allows users to discover items of interest in a minimal number of interactions. We propose generalized linear search (GLS), a combination of linear and generalized searches that brings together the benefits of both approaches. We prove that GLS performs at least as well as generalized search and compare our method to several baselines and heuristics. Our evaluation shows that GLS is liked by the users and achieves the shortest interactions.

show abstract

The user model-based summarize and refine approach improves information presentation in spoken dialog systems

Cited by 5 publications

References 39 publications

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

Using domain knowledge for fostering the collaborative ability of a web dialogue system

Minimal Interaction Search in Recommender Systems

Contact Info

Product

Resources

About