Comparing user simulations for dialogue strategy learning

Ai, H and Litman, D (2011) Comparing user simulations for dialogue strategy learning. ACM Transactions on Speech and Language Processing, 7 (3). ISSN 1550-4875

Plain Text (licence) Available under License : See the attached license file. Download (1kB)

Abstract

Recent studies show that user simulations can be used to generate training corpora for learning dialogue strategies automatically. However, it is unclear what type of simulation is most suitable in a particular task setting. We observe that a simulation which generates random behaviors in a restricted way outperforms simulations that mimic human user behaviors in a statistical way. Our finding suggests that we do not always need to construct a realistic user simulation. Since constructing realistic user simulations is not a trivial task, we can save engineering cost by wisely choosing simulation models that are appropriate for our task. © 2011 ACM.

---

Share

Citation/Export:	Select format... Citation - Text Citation - HTML Endnote BibTex Dublin Core OpenURL MARC (ISO 2709) METS MODS EP3 XML Reference Manager Refer
Social Networking:	Share |

---

Details

Item Type:	Article
Status:	Published
Creators/Authors:	Creators Email Pitt Username ORCID Ai, H Litman, D dlitman@pitt.edu DLITMAN
Centers:	Other Centers, Institutes, Offices, or Units > Learning Research & Development Center
Date:	1 May 2011
Date Type:	Publication
Journal or Publication Title:	ACM Transactions on Speech and Language Processing
Volume:	7
Number:	3
DOI or Unique Handle:	10.1145/1966407.1966414
Schools and Programs:	Dietrich School of Arts and Sciences > Computer Science Dietrich School of Arts and Sciences > Intelligent Systems
Refereed:	Yes
ISSN:	1550-4875
Date Deposited:	30 Jul 2014 20:31
Last Modified:	02 Feb 2019 15:59
URI:	http://d-scholarship.pitt.edu/id/eprint/22558

---

Metrics

Monthly Views for the past 3 years

Plum Analytics

Altmetric.com

---

Actions (login required)

View Item