Reformulation of symptom descriptions in dialogue systems for fault diagnosis: How to ask for clarification?. Issue 145 (January 2021)
- Record Type:
- Journal Article
- Title:
- Reformulation of symptom descriptions in dialogue systems for fault diagnosis: How to ask for clarification?. Issue 145 (January 2021)
- Main Title:
- Reformulation of symptom descriptions in dialogue systems for fault diagnosis: How to ask for clarification?
- Authors:
- Müller, Romy
Paul, Dennis
Li, Yijun - Abstract:
- Highlights: A dialogue system's reformulations of ambiguous user utterances influence performance. Common terms reduce time and verbal effort but tend to be misunderstood when incorrect. Technical terms are not accepted uncritically but lead to more clarification questions. Visual information mitigates the problem of increased error rates for common terms. Verbal alignment with the dialogue system is low but increases with technical terms. Abstract: Psycholinguistic research can inform the design of dialogue systems for fault diagnosis. When users provide ambiguous symptom descriptions, dialogue systems can reformulate these descriptions to check the correctness of their interpretation. The present study investigated whether such reformulations should be performed by users or dialogue systems, and how they should be phrased. In a Wizard-of-Oz study, subjects described faults symptoms to a chatbot, which subsequently asked for clarification. Experiment 1 compared the effects of requests for subjects to self-correct their descriptions and reformulations provided by the dialogue system in either common or technical terms. Experiment 2 combined reformulations in common and technical terms with each other and with pictures of fault symptoms. The results revealed that requests for self-correction increased solution times and verbal effort, that common terms decreased solution times but led to errors when seemingly easy reformulations were incorrect, and that technical terms didHighlights: A dialogue system's reformulations of ambiguous user utterances influence performance. Common terms reduce time and verbal effort but tend to be misunderstood when incorrect. Technical terms are not accepted uncritically but lead to more clarification questions. Visual information mitigates the problem of increased error rates for common terms. Verbal alignment with the dialogue system is low but increases with technical terms. Abstract: Psycholinguistic research can inform the design of dialogue systems for fault diagnosis. When users provide ambiguous symptom descriptions, dialogue systems can reformulate these descriptions to check the correctness of their interpretation. The present study investigated whether such reformulations should be performed by users or dialogue systems, and how they should be phrased. In a Wizard-of-Oz study, subjects described faults symptoms to a chatbot, which subsequently asked for clarification. Experiment 1 compared the effects of requests for subjects to self-correct their descriptions and reformulations provided by the dialogue system in either common or technical terms. Experiment 2 combined reformulations in common and technical terms with each other and with pictures of fault symptoms. The results revealed that requests for self-correction increased solution times and verbal effort, that common terms decreased solution times but led to errors when seemingly easy reformulations were incorrect, and that technical terms did not mislead subjects into accepting them uncritically. Enrichments with pictures reduced the risk of accepting incorrect reformulations and were considered particularly helpful when combined with common terms. Lexical alignment with dialogue system reformulations was low, but subjects adopted its technical terms most readily when no common terms were provided. Taken together, the results suggest that combining reformulations in everyday language with visual information is most suitable to support grounding. … (more)
- Is Part Of:
- International journal of human-computer studies. Issue 145(2021)
- Journal:
- International journal of human-computer studies
- Issue:
- Issue 145(2021)
- Issue Display:
- Volume 145, Issue 145 (2021)
- Year:
- 2021
- Volume:
- 145
- Issue:
- 145
- Issue Sort Value:
- 2021-0145-0145-0000
- Page Start:
- Page End:
- Publication Date:
- 2021-01
- Subjects:
- Dialogue system -- Fault diagnosis -- Grounding -- Miscommunication -- Repair -- Reformulation
Human-machine systems -- Periodicals
Systems engineering -- Periodicals
Human engineering -- Periodicals
Human engineering
Human-machine systems
Systems engineering
Periodicals
Electronic journals
004.019 - Journal URLs:
- http://www.sciencedirect.com/science/journal/10715819 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.ijhcs.2020.102516 ↗
- Languages:
- English
- ISSNs:
- 1071-5819
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 4542.288100
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 14790.xml