Detecting Inappropriate Clarification Requests in Spoken Dialogue Systems
نویسندگان
چکیده
Spoken Dialogue Systems ask for clarification when they think they have misunderstood users. Such requests may differ depending on the information the system believes it needs to clarify. However, when the error type or location is misidentified, clarification requests appear confusing or inappropriate. We describe a classifier that identifies inappropriate requests, trained on features extracted from user responses in laboratory studies. This classifier achieves 88.5% accuracy and .885 Fmeasure in detecting such requests.
منابع مشابه
Clarification questions to improve dialogue flow and speech recognition in spoken dialogue systems
Within human-machine conversation, clarification is vital and may consist of various forms, as it is may by due to many different effects on different levels of communication. In this paper, we present a strategy for detecting situations where a need for clarification exists in a natural spoken dialogue system. We define rule sets which enable us, via an anomaly analysis, to detect these critic...
متن کاملClarification in Spoken Dialogue Systems
This paper argues for the use of more natural and flexible clarification questions in spoken dialogue systems. Several forms and aspects of clarification questions are discussed and exemplified by examples from human-human dialogue corpora. We show how clarification questions fit into the broader context of miscommunication and describe the types of information spoken dialogue systems need in o...
متن کاملGALATEA: A Discourse Modeller Supporting Concept-level Error Handling in Spoken Dialogue Systems
In this paper, a discourse modeller for conversational spoken dialogue systems, called GALATEA, is presented. Apart from handling the resolution of ellipses and anaphora, it tracks the “grounding status” of concepts that are mentioned during the discourse, i.e. information about who said what when. This grounding information also contains concept confidence scores that are derived from the spee...
متن کاملModelling Human Clarification Strategies
We model human responses to speech recognition errors from a corpus of human clarification strategies. We employ learning techniques to study 1) the decision to either stop and ask a clarification question or to continue the dialogue without clarification, and 2) the decision to ask a targeted clarification question or a more generic question. Targeted clarification questions focus specifically...
متن کاملThe effects of prosodic features on the interpretation of clarification ellipses
In this paper, the effects of prosodic features on the interpretation of elliptical clarification requests in dialogue are studied. An experiment is presented where subjects were asked to listen to short human-computer dialogue fragments in Swedish, where a synthetic voice was making an elliptical clarification after a user turn. The prosodic features of the synthetic voice were systematically ...
متن کامل