Break, Repair, Learn, Break Less: Investigating User Preferences for Assignment of Divergent Phrasing Learning Burden in Human-Agent Interaction to Minimize Conversational Breakdowns

Mina Foosherian*, S. Kernan Freire, E. Niforatos, Karl A. Hribernik, Klaus-Dieter Thoben

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
46 Downloads (Pure)

Abstract

Conversational agents (CA) occasionally fail to understand the user's intention or respond inappropriately due to natural language complexity. These conversational breakdowns can happen because of low intent and entity prediction confidence scores. A promising repair strategy in such cases is that the CA proposes to users likely alternatives to proceed. If one of these options matches the user's intention, the breakdown is repaired successfully. We propose that successful repairs should be followed by a learning mechanism to minimize future breakdowns. After a successful repair, the CA, user, or both can learn each other's specific phrasing. This prevents similar phrasings from causing reoccurring breakdowns. We compared user preferences for these learning mechanisms in a scenario-based study with manufacturing workers (). Our result showed that users first prefer to share the learning burden with the CA (61.3%), followed by entirely outsourcing the learning burden to the CA (60.7%) as opposed to themselves.

Original languageEnglish
Title of host publicationProceedings of MUM 2022, the 21st International Conference on Mobile and Ubiquitous Multimedia
EditorsTanja Doring, Susanne Boll, Ashley Colley, Augusto Esteves, Joao Guerreiro
PublisherAssociation for Computing Machinery (ACM)
Pages151-158
Number of pages8
ISBN (Electronic)9781450398213
ISBN (Print)978-1-4503-9820-6
DOIs
Publication statusPublished - 2022
EventMUM '22: 21st International Conference on Mobile and Ubiquitous Multimedia - Lisbon, Portugal
Duration: 27 Nov 202230 Nov 2022

Publication series

NameACM International Conference Proceeding Series

Conference

ConferenceMUM '22: 21st International Conference on Mobile and Ubiquitous Multimedia
Country/TerritoryPortugal
CityLisbon
Period27/11/2230/11/22

Keywords

  • Human centered AI
  • Learning
  • Conversational Breakdown
  • Conversational Agents
  • User Experience
  • Error Handling

Fingerprint

Dive into the research topics of 'Break, Repair, Learn, Break Less: Investigating User Preferences for Assignment of Divergent Phrasing Learning Burden in Human-Agent Interaction to Minimize Conversational Breakdowns'. Together they form a unique fingerprint.

Cite this