Results 1 - 10
of
16
The Theory and Use of Clarification Requests in Dialogue
, 2004
"... Clarification requests are an important, relatively common and yet under-studied dialogue device allowing a user to ask about some feature (e.g. the meaning or form) of an utterance, or part thereof. They can take many different forms (often highly elliptical) and can have many different meanings (r ..."
Abstract
-
Cited by 26 (4 self)
- Add to MetaCart
Clarification requests are an important, relatively common and yet under-studied dialogue device allowing a user to ask about some feature (e.g. the meaning or form) of an utterance, or part thereof. They can take many different forms (often highly elliptical) and can have many different meanings (requesting various types of information). This thesis combines empirical, theoretical and implementational work to provide a study of the various types of clarification request that exist, give a theoretical analysis thereof, and show how the results can be applied to add useful capabilities to a prototype computational dialogue system. A series
Form, Intonation and Function of Clarification Requests In German Task-Oriented . . .
- IN PROCEEDINGS OF CATALOG '04 (THE 8TH WORKSHOP ON THE SEMANTICS AND PRAGMATICS OF DIALOGUE, SEMDIAL04
, 2004
"... We present a classification-scheme for describing the form (including intonation) and function of clarification requests (CRs) that is more fine-grained than extant classifications, and a study of a corpus of German task-oriented dialogues where we used this scheme to annotate the occuring CR ..."
Abstract
-
Cited by 22 (3 self)
- Add to MetaCart
We present a classification-scheme for describing the form (including intonation) and function of clarification requests (CRs) that is more fine-grained than extant classifications, and a study of a corpus of German task-oriented dialogues where we used this scheme to annotate the occuring CRs. Among the correlations between form and function we found was a hitherto undescribed correlation between intonation of CRs and their interpretation, which could possibly aid dialogue systems in interpreting CRs.
GALATEA: A Discourse Modeller Supporting Concept-level Error Handling in Spoken Dialogue Systems
- In Proceedings of SigDial
, 2005
"... 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. ..."
Abstract
-
Cited by 21 (8 self)
- Add to MetaCart
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 speech recogniser word confidence scores. The discourse model may then be used for concept-level error handling, i.e. grounding of concepts, fragmentary clarification requests, and detection of erroneous concepts in the model at later stages in the dialogue. 1
The Effects of Prosodic Features on the Interpretation Of Clarification Ellispes
, 2005
"... 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 c ..."
Abstract
-
Cited by 18 (11 self)
- Add to MetaCart
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 varied, and the subjects were asked to judge what was actually intended by the computer. The results show that an early low F0 peak signals acceptance, that a late high peak is perceived as a request for clarification of what was said, and that a mid high peak is perceived as a request for clarification of the meaning of what was said. The study can be seen as the beginnings of a tentative model for intonation of clarification ellipses in Swedish, which can be implemented and tested in spoken dialogue systems.
Clarifying spatial descriptions: Local and global effects on semantic co-ordination
- in Proc. 10 th Workshop on the Semantics and Pragmatics of Dialogue. 2006
"... A key problem for models of dialogue is to explain the mechanisms involved in generating and responding to clarification requests. We report a 'Maze task ' experi-ment that investigates the effect of ‘spoof ’ clarification requests on the de-velopment of semantic co-ordination. The result ..."
Abstract
-
Cited by 9 (2 self)
- Add to MetaCart
A key problem for models of dialogue is to explain the mechanisms involved in generating and responding to clarification requests. We report a 'Maze task ' experi-ment that investigates the effect of ‘spoof ’ clarification requests on the de-velopment of semantic co-ordination. The results provide evidence of both lo-cal and global semantic co-ordination phenomena that are not captured by ex-isting dialogue co-ordination models. 1
CLARIE: Handling Clarification Requests in a Dialogue System
, 2006
"... This paper sets out a approach to clarification requests (CRs) general enough to cover all the major forms found in corpus data and specific enough to analyse the questions they ask about individual words and phrases. Its main features are a view of utterances as contextual abstracts with a radical ..."
Abstract
-
Cited by 9 (0 self)
- Add to MetaCart
This paper sets out a approach to clarification requests (CRs) general enough to cover all the major forms found in corpus data and specific enough to analyse the questions they ask about individual words and phrases. Its main features are a view of utterances as contextual abstracts with a radically abstracted semantic representation, and a view of CRs as standard utterances asking standard questions, but showing a particular kind of contextual dependence. It shows how it can be implemented computationally within a prototype text-based dialogue system, CLARIE, allowing it not only to generate CRs to clarify unknown reference and learn new words, but also to interpret and respond to user CRs, with both capabilities integrated within the standard dialogue processes and governed by empirical evidence.
A WOz Framework for Exploring Miscommunication in HRI
"... Abstract. The aim of this paper is to investigate management of miscommunication in spontaneous interaction between a human and a speech-enabled robot. The paper describes initial results of an exploratory WOz study, in which pairs of naive participants interacted and collaborated in a navigation ta ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Abstract. The aim of this paper is to investigate management of miscommunication in spontaneous interaction between a human and a speech-enabled robot. The paper describes initial results of an exploratory WOz study, in which pairs of naive participants interacted and collaborated in a navigation task. The study is motivated by how humans achieve mutual understanding as well as previous research conducted in the area of spoken dialogue systems. The dialogue and error handling capacity of the wizard is incrementally impaired towards the capabilities of a system in three experimental conditions. Preliminary analysis of the data reveals the necessity to endow the robot with richer error management resources and point to the efficacy of less explicit error handling strategies. Analysis of the data and further experimentation are currently performed and expected soon to shed light to some of the intricacies and unique characteristics of HRI. 1
Prosodic Features in the Perception of Clarification Ellipses
"... We present an experiment where subjects were asked to listen to Swedish human-computer dialogue fragments where a synthetic voice makes an elliptical clarification after a user turn. The prosodic features of the synthetic voice were systematically varied, and subjects were asked to judge the compute ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
We present an experiment where subjects were asked to listen to Swedish human-computer dialogue fragments where a synthetic voice makes an elliptical clarification after a user turn. The prosodic features of the synthetic voice were systematically varied, and subjects were asked to judge the computer’s actual intention. The results show that an early low F0 peak signals acceptance, that a late high peak is perceived as a request for clarification of what was said, and that a mid high peak is perceived as a request for clarification of the meaning of what was said. The study can be seen as the beginnings of a tentative model for intonation of clarification ellipses in Swedish, which can be implemented and tested in spoken dialogue systems.
Towards a Dialog Strategy for Handling Miscommunication in Human-Robot Dialog
"... Abstract — This paper presents a first theoretical framework for a dialog strategy handling miscommunication in natural language Human-Robot Interaction (HRI). On the one hand the dialog strategy is deduced from findings about humanhuman communication patterns and coping strategies for miscommunicat ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract — This paper presents a first theoretical framework for a dialog strategy handling miscommunication in natural language Human-Robot Interaction (HRI). On the one hand the dialog strategy is deduced from findings about humanhuman communication patterns and coping strategies for miscommunication. On the other hand, relevant cognitive theories concerning human perception serve as a conceptual basis for the dialog strategy. The novel approach is firstly to combine these communication patterns with coping strategies and cognitive theories from human-human interaction (HHI) and secondly transfer them to HRI as a general dialog strategy for handling miscommunication. The presented approach is applicable to any task-oriented dialog. In a first step the conversational context is confined to route descriptions, given that asking for directions is an restricted but nevertheless challenging example for taskoriented dialog between humans and a robot. I.
discussion, help and advice:
"... In this thesis, I present strategies to improve the robustness and naturalness of dialogue sys-tems by asking fragmentary Clarification Requests (CRs) on several levels according to Con-fidence Scores. In a corpus study I gather evidence how clarifications are realised in human-human communication. ..."
Abstract
- Add to MetaCart
In this thesis, I present strategies to improve the robustness and naturalness of dialogue sys-tems by asking fragmentary Clarification Requests (CRs) on several levels according to Con-fidence Scores. In a corpus study I gather evidence how clarifications are realised in human-human communication. I demonstrate how different functions of CRs map on surface forms for the travel booking domain, and what kind of grounding strategy should be prefered for task-oriented dialogues. Based on these results, I sketch a prototype dialogue system how to generate fragmentary clarifications on several levels. Finally, I am discussing the problem of asking multiple Clarification Requests concerning one utterance. i
