Author ORCID Identifier
Computer Sciences, Information Science, Robotics and automatic control, Communication engineering and systems, Social sciences, Linguistics
Confusion is a mental state that can be triggered in task-oriented interactions and which can if left unattended lead to boredom, frustration, or disengagement from the task at hand. Since previous work has demonstrated that confusion can be detected in embodied situated interactions from visual and auditory cues, in this technique report, we propose appropriate interaction structures which should be used to mitigate confusion. We motivate and describe this dialogue mechanism through an information state-style policy with examples, and also outline the approach we are taking to integrate such a meta-conversational goal alongside core task-oriented considerations in modern data driven conversational techniques. While the current policy design is a starting point, we believe it raises some interesting challenges for the integration of a reusable meta-conversational policy with highly data-driven approaches which have been enabled by large language models.
Li, N., & Ross, R. J. (2023). Technique Report: A Framework for Confusion Mitigation in Task-Oriented Interactions. Technological University Dublin. DOI: 10.21427/C3R6-RB43
Science Foundation Ireland
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.