Award Abstract #0744904
Incremental Wizard Ablation: A Novel WOz Paradigm for Learning, Testing and Evaluating Human-Machine Dialogue using Parameterized Corpora
![](common/images/greenline.jpg)
NSF Org: |
IIS
Division of Information & Intelligent Systems
|
![divider line](common/images/x.gif) |
![divider line](common/images/x.gif) |
Initial Amendment Date: |
September 25, 2007 |
![divider line](common/images/x.gif) |
Latest Amendment Date: |
April 10, 2009 |
![divider line](common/images/x.gif) |
Award Number: |
0744904 |
![divider line](common/images/x.gif) |
Award Instrument: |
Standard Grant |
![divider line](common/images/x.gif) |
Program Manager: |
Tatiana D. Korelsky
IIS Division of Information & Intelligent Systems
CSE Directorate for Computer & Information Science & Engineering
|
![divider line](common/images/x.gif) |
Start Date: |
October 1, 2007 |
![divider line](common/images/x.gif) |
Expires: |
September 30, 2010 (Estimated) |
![divider line](common/images/x.gif) |
Awarded Amount to Date: |
$233685 |
![divider line](common/images/x.gif) |
Investigator(s): |
Susan Epstein susan.epstein@hunter.cuny.edu (Principal Investigator)
|
![divider line](common/images/x.gif) |
Sponsor: |
CUNY Hunter College
695 Park Avenue
New York, NY 10065 212/772-4020
|
![divider line](common/images/x.gif) |
NSF Program(s): |
ROBUST INTELLIGENCE
|
![divider line](common/images/x.gif) |
Field Application(s): |
0116000 Human Subjects
|
![divider line](common/images/x.gif) |
Program Reference Code(s): |
SMET, OTHR, HPCC, 9251, 9218, 9178, 7495, 0000
|
![divider line](common/images/x.gif) |
Program Element Code(s): |
7495
|
ABSTRACT
![](common/images/bluefade.jpg)
Automated telephone dialog systems rely disproportionately on accurate transcription of the speech signal into readable text. When the system has low confidence in the automatic speech transcription
(ASR) of a caller's utterance, a typical dialog strategy requires the system to repeat its best guess, and ask for confirmation. This leads to unnatural interactions and dissatisfied callers. The current project focuses on developing better dialog strategies given current ASR capabilities by learning automatically from contrasting
corpora, and comparing the results. Using a novel methodology, wizard ablation, simulated human-system dialogs are collected that vary in controlled ways. The testbed application, an Automated Readers Advisor for New York City's Andrew Heiskell Talking Book and Braille Library, has appropriately limited complexity, and
potentially broad social benefit.
The motivation for wizard ablation is that research is needed into the problem-solving strategies humans would use if the human communication channel were restricted to be more like a machine's. In conventional wizard-of-oz studies, unsuspecting users interact with human wizards "behind-the-screen", thus providing data on the way humans interact with (what they believe to be) machines. Unlike a conventional wizard, an ablated wizard is restricted to seeing the ASR input to the system dialog manager. Under a further ablation
condition, the wizard must choose actions from the repertoire that the system uses, but can combine them freely. The book-borrowing scenarios for the wizard interactions have been designed to be realistic, and Heiskell Library patrons participate in the studies. The collected dialogs will be made available to the community.
Please report errors in award information by writing to: awardsearch@nsf.gov.
|