Generating varied narrative probability exercises

Mariet Theune, Roan Boer Rookhuiszen, Hendrikus J.A. op den Akker, Hanneke Geerlings

Abstract

This paper presents Genpex, a system for automatic generation of narrative probability exercises. Generation of exercises in Genpex is done in two steps. First, the system creates a specification of a solvable probability problem, based on input from the user (a researcher or test developer) who selects a specific question type and a narrative context for the problem. Then, a text expressing the probability problem is generated. The user can tune the generated text by setting the values of some linguistic variation parameters. By varying the mathematical content of the exercise, its narrative context and the linguistic parameter settings, many different exercises can be produced. Here we focus on the natural language generation part of Genpex. After describing how the system works, we briefly present our first evaluation results, and discuss some aspects requiring further investigation.
Original languageUndefined
Title of host publicationProceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011
EditorsJ. Tetreault, J. Burstein, C. Leacock
Place of PublicationPortland, Oregon
PublisherAssociation for Computational Linguistics
Pages20-29
Number of pages10
ISBN (Print)978-1-93728-403-9
StatePublished - Jun 2011

Publication series

Name
PublisherAssociation for Computational Linguistics

Fingerprint

Linguistics
Specifications

Keywords

  • IR-78604
  • EWI-20801
  • METIS-282124

Cite this

Theune, M., Boer Rookhuiszen, R., op den Akker, H. J. A., & Geerlings, H. (2011). Generating varied narrative probability exercises. In J. Tetreault, J. Burstein, & C. Leacock (Eds.), Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011 (pp. 20-29). Portland, Oregon: Association for Computational Linguistics.

Theune, Mariet; Boer Rookhuiszen, Roan; op den Akker, Hendrikus J.A.; Geerlings, Hanneke / Generating varied narrative probability exercises.

Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011. ed. / J. Tetreault; J. Burstein; C. Leacock. Portland, Oregon : Association for Computational Linguistics, 2011. p. 20-29.

Research output: Scientific - peer-reviewConference contribution

@inbook{f9648f305dd94ccd8fc84b3b1dd72141,
title = "Generating varied narrative probability exercises",
abstract = "This paper presents Genpex, a system for automatic generation of narrative probability exercises. Generation of exercises in Genpex is done in two steps. First, the system creates a specification of a solvable probability problem, based on input from the user (a researcher or test developer) who selects a specific question type and a narrative context for the problem. Then, a text expressing the probability problem is generated. The user can tune the generated text by setting the values of some linguistic variation parameters. By varying the mathematical content of the exercise, its narrative context and the linguistic parameter settings, many different exercises can be produced. Here we focus on the natural language generation part of Genpex. After describing how the system works, we briefly present our first evaluation results, and discuss some aspects requiring further investigation.",
keywords = "IR-78604, EWI-20801, METIS-282124",
author = "Mariet Theune and {Boer Rookhuiszen}, Roan and {op den Akker}, {Hendrikus J.A.} and Hanneke Geerlings",
year = "2011",
month = "6",
isbn = "978-1-93728-403-9",
publisher = "Association for Computational Linguistics",
pages = "20--29",
editor = "J. Tetreault and J. Burstein and C. Leacock",
booktitle = "Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011",

}

Theune, M, Boer Rookhuiszen, R, op den Akker, HJA & Geerlings, H 2011, Generating varied narrative probability exercises. in J Tetreault, J Burstein & C Leacock (eds), Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011. Association for Computational Linguistics, Portland, Oregon, pp. 20-29.

Generating varied narrative probability exercises. / Theune, Mariet; Boer Rookhuiszen, Roan; op den Akker, Hendrikus J.A.; Geerlings, Hanneke.

Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011. ed. / J. Tetreault; J. Burstein; C. Leacock. Portland, Oregon : Association for Computational Linguistics, 2011. p. 20-29.

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Generating varied narrative probability exercises

AU - Theune,Mariet

AU - Boer Rookhuiszen,Roan

AU - op den Akker,Hendrikus J.A.

AU - Geerlings,Hanneke

PY - 2011/6

Y1 - 2011/6

N2 - This paper presents Genpex, a system for automatic generation of narrative probability exercises. Generation of exercises in Genpex is done in two steps. First, the system creates a specification of a solvable probability problem, based on input from the user (a researcher or test developer) who selects a specific question type and a narrative context for the problem. Then, a text expressing the probability problem is generated. The user can tune the generated text by setting the values of some linguistic variation parameters. By varying the mathematical content of the exercise, its narrative context and the linguistic parameter settings, many different exercises can be produced. Here we focus on the natural language generation part of Genpex. After describing how the system works, we briefly present our first evaluation results, and discuss some aspects requiring further investigation.

AB - This paper presents Genpex, a system for automatic generation of narrative probability exercises. Generation of exercises in Genpex is done in two steps. First, the system creates a specification of a solvable probability problem, based on input from the user (a researcher or test developer) who selects a specific question type and a narrative context for the problem. Then, a text expressing the probability problem is generated. The user can tune the generated text by setting the values of some linguistic variation parameters. By varying the mathematical content of the exercise, its narrative context and the linguistic parameter settings, many different exercises can be produced. Here we focus on the natural language generation part of Genpex. After describing how the system works, we briefly present our first evaluation results, and discuss some aspects requiring further investigation.

KW - IR-78604

KW - EWI-20801

KW - METIS-282124

M3 - Conference contribution

SN - 978-1-93728-403-9

SP - 20

EP - 29

BT - Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011

PB - Association for Computational Linguistics

ER -

Theune M, Boer Rookhuiszen R, op den Akker HJA, Geerlings H. Generating varied narrative probability exercises. In Tetreault J, Burstein J, Leacock C, editors, Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications (BEA-6) at ACL-HLT 2011. Portland, Oregon: Association for Computational Linguistics. 2011. p. 20-29.