scispace - formally typeset
Proceedings ArticleDOI

Wizard of Oz studies: why and how

Nils Dahlbäck, +2 more
- Vol. 6, Iss: 4, pp 193-200
Reads0
Chats0
TLDR
It is concluded that empirical studies of the unique qualities of man-machine interaction as distinct from general human discourse are required for the development of user-friendly interactive systems.
Abstract
Current approaches to the development of natural language dialogue systems are discussed, and it is claimed that they do not sufficiently consider the unique qualities of man-machine interaction as distinct from general human discourse. It is concluded that empirical studies of this unique communication situation are required for the development of user-friendly interactive systems. One way of achieving this is through the use of so-called Wizard of Oz studies. The focus of the work described in the paper is on the practical execution of the studies and the methodological conclusions drawn on the basis of the authors' experience. While the focus is on natural language interfaces, the methods used and the conclusions drawn from the results obtained are of relevance also to other kinds of intelligent interfaces.

read more

Content maybe subject to copyright    Report

Citations
More filters
Posted Content

Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management

TL;DR: The Conversation Graph is proposed, a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents.
DissertationDOI

Facilitating Collaboration among Children with Autism through Robot-assisted Play

Joshua Wainer
TL;DR: In this paper, the authors discuss how autonomous robots can be used to foster and support collaborative play among children with autism in a number of different settings, such as arena games and collaborative video games.
Proceedings ArticleDOI

Supporting the wizard: interface improvements in Wizard of Oz studies

TL;DR: Two experiments aimed at exploring the wizard task in order to inform the design of a univerals wizard interface for testing LTCs are reported on.

A coding scheme for the annotation of feedback phenomena in conversational speech

TL;DR: A coding scheme specifically developed to label feedback phenomena in conversational speech is presented, which allows the categorization of feedback phenomena according to their typology, direction, and communicative function in the given context.
Proceedings ArticleDOI

An evaluation of virtual human technology in informational kiosks

TL;DR: This paper presents findings from studies of three different information kiosk applications, and describes the application, the participants, and the results, with specific focus on how to increased user participation and improved informational throughput.
References
More filters
Journal ArticleDOI

The development of communication skills: modifications in the speech of young children as a function of listener

TL;DR: This paper found that the 4-year-old adjusted his speech with regard to the changing capacities of different-aged listeners, and the younger the 2-year old, the greater was the observed speech adjustment.
Journal ArticleDOI

Cross-linguistic differences in parsing: Restrictions on the use of the Late Closure strategy in Spanish ☆

TL;DR: The results throw doubt on the suggestion that the Late Closure strategy is favoured (in English) mainly because it is efficient in information processing terms and suggest that different languages make use of parsing strategies in an essentially arbitrary way.
Journal ArticleDOI

Simulating speech systems

TL;DR: The “Wizard of Oz” technique for simulating future interactive technology and a partial taxonomy of such simulations is reviewed and a general Wizard of Oz methodology is suggested.