Galatea: A Discourse Modeller Supporting Concept-Level Error Handling in Spoken Dialogue Systems

Skantze, Gabriel

doi:10.1007/978-1-4020-6821-8_7

Cited by 32 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For discourse modelling, the HIGGINS module GALATEA (Skantze, 2008) has been extended to operate incrementally. The task of GALATEA is to interpret utterances in their context by transforming ellipses into full propositions, indentify discourse entities, resolve anaphora and keep track of the grounding status of concepts (their confidence score and when they have been grounded in the discourse).…”

Section: Discourse Modellingmentioning

confidence: 99%

Incremental dialogue processing in a micro-domain

Skantze

Schlangen

2009

Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09

Self Cite

View full text Add to dashboard Cite

This paper describes a fully incremental dialogue system that can engage in dialogues in a simple domain, number dictation. Because it uses incremental speech recognition and prosodic analysis, the system can give rapid feedback as the user is speaking, with a very short latency of around 200ms. Because it uses incremental speech synthesis and self-monitoring, the system can react to feedback from the user as the system is speaking. A comparative evaluation shows that naïve users preferred this system over a non-incremental version, and that it was perceived as more human-like.

show abstract

Section: Discourse Modellingmentioning

confidence: 99%

Incremental dialogue processing in a micro-domain

Skantze

Schlangen

2009

Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09

Self Cite

View full text Add to dashboard Cite

show abstract

“…The words are parsed by an Interpreter [30] which tries to find an optimal sequence of matching phrases from a predefined grammar. These understood phrases are then re-interpreted by a Contextualizer [31], based on the history of the conversation. For example, fragmentary utterances like "red" and "yeah", and referring expression like "it", can be interpreted given the previous utterances from both the robot and the user.…”

Section: Vision Systemmentioning

confidence: 99%

Enhanced visual scene understanding through human-robot dialog

Johnson-Roberson

Bohg

Kragić

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a novel human-robot-interaction framework for the purpose of robust visual scene understanding. Without any a-priori knowledge about the scene structure, the task of the robot is to correctly enumerate how many objects there are in the scene and segment them. Our approach builds on top of state-of-the-art computer vision, segmenting stereo reconstructed point clouds into object hypotheses. This process is combined with a natural dialog system. By putting a 'human in the loop' and exploiting the natural conversation of an advanced dialog system, the robot gains knowledge about ambiguous situations beyond its own resolution. Specifically, we are introducing an entropy-based system allowing the robot to detect the poorest object hypotheses and query the user for arbitration. Based on the information obtained from the human-to-robot dialog, the scene segmentation can be re-seeded and thereby improved. We present experimental results on real data that show an improved segmentation performance compared to segmentation without interaction.

show abstract

“…The dialogue system component in DEAL is based on Higgins, a spoken dialogue system developed at KTH (Skantze (2005)). Higgins includes modules for semantic interpretation and analysis.…”

Section: Deal Architecturementioning

confidence: 99%

Embodied conversational agents in computer assisted language learning

Wik¹,

Hjalmarsson²

2009

Speech Communication

112

View full text Add to dashboard Cite

This paper describes two systems using embodied conversational agents (ECAs) for language learning. The first system, called Ville, is a virtual language teacher for vocabulary and pronunciation training. The second system, a dialogue system called DEAL, is a role-playing game for practicing conversational skills. Whereas DEAL acts as a conversational partner with the objective of creating and keeping an interesting dialogue, Ville takes the role of a teacher who guides, encourages and gives feedback to the students.

show abstract

Galatea: A Discourse Modeller Supporting Concept-Level Error Handling in Spoken Dialogue Systems

Cited by 32 publications

References 24 publications

Incremental dialogue processing in a micro-domain

Incremental dialogue processing in a micro-domain

Enhanced visual scene understanding through human-robot dialog

Embodied conversational agents in computer assisted language learning

Contact Info

Product

Resources

About