Diagnosing Natural Language Answers to Support Adaptive Tutoring

Myroslava O. Dzikovska; Gwendolyn E. Campbell; Charles B. Callaway; Natalie B. Steinhauser; Elaine Farrow; Johanna D. Moore; Leslie A. Butler; Colin Matheson

Diagnosing Natural Language Answers to Support Adaptive Tutoring

Myroslava O. Dzikovska
, Gwendolyn E. Campbell
, Charles B. Callaway
, Natalie B. Steinhauser
, Elaine Farrow
, Johanna D. Moore
, Leslie A. Butler
, Colin Matheson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Understanding answers to open-ended explanation questions is important in intelligent tutoring systems. Existing systems use natural language techniques in essay analysis, but revert to scripted interaction with short-answer questions during remediation, making adapting dialogue to individual students difficult. We describe a corpus study that shows that there is a relationship between the types of faulty answers and the remediation strategies that tutors use; that human tutors respond differently to different kinds of correct answers; and that re-stating correct answers is associated with improved learning. We describe a design for a diagnoser based on this study that supports remediation in open-ended questions and provides an analysis of natural language answers that enables adaptive generation of tutorial feedback for both correct and faulty answers

Original language	English
Title of host publication	Twenty-First International Florida Artificial Intelligence Research Society Conference
Editors	David Wilson, H. Chad Lane
Place of Publication	Coconut Grove, Florida, USA
Publisher	AAAI Press
Pages	403-408
Number of pages	6
ISBN (Electronic)	978-1-57735-365-2
Publication status	Published - May 2008
Event	Twenty-First International Florida Artificial Intelligence Research Society Conference - Coconut Grove, Florida, United States Duration: 15 May 2008 → 17 May 2008

Conference

Conference	Twenty-First International Florida Artificial Intelligence Research Society Conference
Country/Territory	United States
City	Coconut Grove, Florida
Period	15/05/08 → 17/05/08

Access to Document

http://homepages.inf.ed.ac.uk/jmoore/papers/flairs08.pdf

Cite this

Dzikovska, M. O., Campbell, G. E., Callaway, C. B., Steinhauser, N. B., Farrow, E., Moore, J. D., Butler, L. A., & Matheson, C. (2008). Diagnosing Natural Language Answers to Support Adaptive Tutoring. In D. Wilson, & H. C. Lane (Eds.), Twenty-First International Florida Artificial Intelligence Research Society Conference (pp. 403-408). AAAI Press. http://homepages.inf.ed.ac.uk/jmoore/papers/flairs08.pdf

@inproceedings{add7022007da40f18433840accb04ded,

title = "Diagnosing Natural Language Answers to Support Adaptive Tutoring",

abstract = "Understanding answers to open-ended explanation questions is important in intelligent tutoring systems. Existing systems use natural language techniques in essay analysis, but revert to scripted interaction with short-answer questions during remediation, making adapting dialogue to individual students difficult. We describe a corpus study that shows that there is a relationship between the types of faulty answers and the remediation strategies that tutors use; that human tutors respond differently to different kinds of correct answers; and that re-stating correct answers is associated with improved learning. We describe a design for a diagnoser based on this study that supports remediation in open-ended questions and provides an analysis of natural language answers that enables adaptive generation of tutorial feedback for both correct and faulty answers",

author = "Dzikovska, \{Myroslava O.\} and Campbell, \{Gwendolyn E.\} and Callaway, \{Charles B.\} and Steinhauser, \{Natalie B.\} and Elaine Farrow and Moore, \{Johanna D.\} and Butler, \{Leslie A.\} and Colin Matheson",

year = "2008",

month = may,

language = "English",

pages = "403--408",

editor = "David Wilson and Lane, \{H. Chad\}",

booktitle = "Twenty-First International Florida Artificial Intelligence Research Society Conference",

publisher = "AAAI Press",

note = "Twenty-First International Florida Artificial Intelligence Research Society Conference ; Conference date: 15-05-2008 Through 17-05-2008",

}

Dzikovska, MO, Campbell, GE, Callaway, CB, Steinhauser, NB, Farrow, E, Moore, JD, Butler, LA & Matheson, C 2008, Diagnosing Natural Language Answers to Support Adaptive Tutoring. in D Wilson & HC Lane (eds), Twenty-First International Florida Artificial Intelligence Research Society Conference. AAAI Press, Coconut Grove, Florida, USA, pp. 403-408, Twenty-First International Florida Artificial Intelligence Research Society Conference, Coconut Grove, Florida, United States, 15/05/08. <http://homepages.inf.ed.ac.uk/jmoore/papers/flairs08.pdf>

Diagnosing Natural Language Answers to Support Adaptive Tutoring. / Dzikovska, Myroslava O.; Campbell, Gwendolyn E.; Callaway, Charles B. et al.
Twenty-First International Florida Artificial Intelligence Research Society Conference. ed. / David Wilson; H. Chad Lane. Coconut Grove, Florida, USA: AAAI Press, 2008. p. 403-408.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Diagnosing Natural Language Answers to Support Adaptive Tutoring

AU - Dzikovska, Myroslava O.

AU - Campbell, Gwendolyn E.

AU - Callaway, Charles B.

AU - Steinhauser, Natalie B.

AU - Farrow, Elaine

AU - Moore, Johanna D.

AU - Butler, Leslie A.

AU - Matheson, Colin

PY - 2008/5

Y1 - 2008/5

N2 - Understanding answers to open-ended explanation questions is important in intelligent tutoring systems. Existing systems use natural language techniques in essay analysis, but revert to scripted interaction with short-answer questions during remediation, making adapting dialogue to individual students difficult. We describe a corpus study that shows that there is a relationship between the types of faulty answers and the remediation strategies that tutors use; that human tutors respond differently to different kinds of correct answers; and that re-stating correct answers is associated with improved learning. We describe a design for a diagnoser based on this study that supports remediation in open-ended questions and provides an analysis of natural language answers that enables adaptive generation of tutorial feedback for both correct and faulty answers

AB - Understanding answers to open-ended explanation questions is important in intelligent tutoring systems. Existing systems use natural language techniques in essay analysis, but revert to scripted interaction with short-answer questions during remediation, making adapting dialogue to individual students difficult. We describe a corpus study that shows that there is a relationship between the types of faulty answers and the remediation strategies that tutors use; that human tutors respond differently to different kinds of correct answers; and that re-stating correct answers is associated with improved learning. We describe a design for a diagnoser based on this study that supports remediation in open-ended questions and provides an analysis of natural language answers that enables adaptive generation of tutorial feedback for both correct and faulty answers

M3 - Conference contribution

SP - 403

EP - 408

BT - Twenty-First International Florida Artificial Intelligence Research Society Conference

A2 - Wilson, David

A2 - Lane, H. Chad

PB - AAAI Press

CY - Coconut Grove, Florida, USA

T2 - Twenty-First International Florida Artificial Intelligence Research Society Conference

Y2 - 15 May 2008 through 17 May 2008

ER -

Diagnosing Natural Language Answers to Support Adaptive Tutoring

Abstract

Conference

Access to Document

Fingerprint

Cite this