Representation and reasoning for deeper natural language understanding in a physics tutoring system

Maxim Makatchev, Kurt VanLehn, Pamela W. Jordan, Umarani Pappuswamy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Students' natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of "proper" domain statements. Analyzing such input and providing appropriate tutorial feedback requires extracting information relevant to the physics domain and diagnosing this information for possible errors and gaps in reasoning. In this paper we will describe two approaches to solving the diagnosis problem: weighted abductive reasoning and assumption-based truth maintenance system (ATMS). We also outline the features of knowledge representation (KR) designed to capture relevant semantics and to facilitate computational feasibility.

Original languageEnglish (US)
Title of host publicationFLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference
Pages682-687
Number of pages6
Volume2006
StatePublished - 2006
Externally publishedYes
EventFLAIRS 2006 - 19th International Florida Artificial Intelligence Research Society Conference - Melbourne Beach, FL, United States
Duration: May 11 2006May 13 2006

Other

OtherFLAIRS 2006 - 19th International Florida Artificial Intelligence Research Society Conference
CountryUnited States
CityMelbourne Beach, FL
Period5/11/065/13/06

Fingerprint

Knowledge representation
Mechanics
Physics
Semantics
Students
Feedback

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Makatchev, M., VanLehn, K., Jordan, P. W., & Pappuswamy, U. (2006). Representation and reasoning for deeper natural language understanding in a physics tutoring system. In FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference (Vol. 2006, pp. 682-687)

Representation and reasoning for deeper natural language understanding in a physics tutoring system. / Makatchev, Maxim; VanLehn, Kurt; Jordan, Pamela W.; Pappuswamy, Umarani.

FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference. Vol. 2006 2006. p. 682-687.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Makatchev, M, VanLehn, K, Jordan, PW & Pappuswamy, U 2006, Representation and reasoning for deeper natural language understanding in a physics tutoring system. in FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference. vol. 2006, pp. 682-687, FLAIRS 2006 - 19th International Florida Artificial Intelligence Research Society Conference, Melbourne Beach, FL, United States, 5/11/06.
Makatchev M, VanLehn K, Jordan PW, Pappuswamy U. Representation and reasoning for deeper natural language understanding in a physics tutoring system. In FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference. Vol. 2006. 2006. p. 682-687
Makatchev, Maxim ; VanLehn, Kurt ; Jordan, Pamela W. ; Pappuswamy, Umarani. / Representation and reasoning for deeper natural language understanding in a physics tutoring system. FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference. Vol. 2006 2006. pp. 682-687
@inproceedings{61dde186b7564d2aa737d7100187656a,
title = "Representation and reasoning for deeper natural language understanding in a physics tutoring system",
abstract = "Students' natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of {"}proper{"} domain statements. Analyzing such input and providing appropriate tutorial feedback requires extracting information relevant to the physics domain and diagnosing this information for possible errors and gaps in reasoning. In this paper we will describe two approaches to solving the diagnosis problem: weighted abductive reasoning and assumption-based truth maintenance system (ATMS). We also outline the features of knowledge representation (KR) designed to capture relevant semantics and to facilitate computational feasibility.",
author = "Maxim Makatchev and Kurt VanLehn and Jordan, {Pamela W.} and Umarani Pappuswamy",
year = "2006",
language = "English (US)",
volume = "2006",
pages = "682--687",
booktitle = "FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference",

}

TY - GEN

T1 - Representation and reasoning for deeper natural language understanding in a physics tutoring system

AU - Makatchev, Maxim

AU - VanLehn, Kurt

AU - Jordan, Pamela W.

AU - Pappuswamy, Umarani

PY - 2006

Y1 - 2006

N2 - Students' natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of "proper" domain statements. Analyzing such input and providing appropriate tutorial feedback requires extracting information relevant to the physics domain and diagnosing this information for possible errors and gaps in reasoning. In this paper we will describe two approaches to solving the diagnosis problem: weighted abductive reasoning and assumption-based truth maintenance system (ATMS). We also outline the features of knowledge representation (KR) designed to capture relevant semantics and to facilitate computational feasibility.

AB - Students' natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of "proper" domain statements. Analyzing such input and providing appropriate tutorial feedback requires extracting information relevant to the physics domain and diagnosing this information for possible errors and gaps in reasoning. In this paper we will describe two approaches to solving the diagnosis problem: weighted abductive reasoning and assumption-based truth maintenance system (ATMS). We also outline the features of knowledge representation (KR) designed to capture relevant semantics and to facilitate computational feasibility.

UR - http://www.scopus.com/inward/record.url?scp=33746069329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746069329&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33746069329

VL - 2006

SP - 682

EP - 687

BT - FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference

ER -