Assessing student paraphrases using lexical semantics and word weighting

Vasile Rus, Mihai Lintean, Art Graesser, Danielle McNamara

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

13 Citations (Scopus)

Abstract

We present in this paper an approach to assessing student paraphrases in the intelligent tutoring system iSTART. The approach is based on measuring the semantic similarity between a student paraphrase and a reference text, called the textbase. The semantic similarity is estimated using knowledge-based word relatedness measures. The relatedness measures rely on knowledge encoded in Word-Net, a lexical database of English. We also experiment with weighting words based on their importance. The word importance information was derived from an analysis of word distributions in 2,225,726 documents from Wikipedia. Performance is reported for 12 different models which resulted from combining 3 different relatedness measures, 2 word sense disambiguation methods, and 2 word-weighting schemes. Furthermore, comparisons are made to other approaches such as Latent Semantic Analysis and the Entailer.

Original languageEnglish (US)
Title of host publicationFrontiers in Artificial Intelligence and Applications
Pages165-172
Number of pages8
Volume200
Edition1
DOIs
StatePublished - 2009
Externally publishedYes

Publication series

NameFrontiers in Artificial Intelligence and Applications
Number1
Volume200
ISSN (Print)09226389

Fingerprint

Semantics
Students
Intelligent systems
Experiments

Keywords

  • Intelligent tutoring systems
  • Natural language processing

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Rus, V., Lintean, M., Graesser, A., & McNamara, D. (2009). Assessing student paraphrases using lexical semantics and word weighting. In Frontiers in Artificial Intelligence and Applications (1 ed., Vol. 200, pp. 165-172). (Frontiers in Artificial Intelligence and Applications; Vol. 200, No. 1). https://doi.org/10.3233/978-1-60750-028-5-165

Assessing student paraphrases using lexical semantics and word weighting. / Rus, Vasile; Lintean, Mihai; Graesser, Art; McNamara, Danielle.

Frontiers in Artificial Intelligence and Applications. Vol. 200 1. ed. 2009. p. 165-172 (Frontiers in Artificial Intelligence and Applications; Vol. 200, No. 1).

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

Rus, V, Lintean, M, Graesser, A & McNamara, D 2009, Assessing student paraphrases using lexical semantics and word weighting. in Frontiers in Artificial Intelligence and Applications. 1 edn, vol. 200, Frontiers in Artificial Intelligence and Applications, no. 1, vol. 200, pp. 165-172. https://doi.org/10.3233/978-1-60750-028-5-165
Rus V, Lintean M, Graesser A, McNamara D. Assessing student paraphrases using lexical semantics and word weighting. In Frontiers in Artificial Intelligence and Applications. 1 ed. Vol. 200. 2009. p. 165-172. (Frontiers in Artificial Intelligence and Applications; 1). https://doi.org/10.3233/978-1-60750-028-5-165
Rus, Vasile ; Lintean, Mihai ; Graesser, Art ; McNamara, Danielle. / Assessing student paraphrases using lexical semantics and word weighting. Frontiers in Artificial Intelligence and Applications. Vol. 200 1. ed. 2009. pp. 165-172 (Frontiers in Artificial Intelligence and Applications; 1).
@inproceedings{9fa0bd0493094485b978513b5b43a85b,
title = "Assessing student paraphrases using lexical semantics and word weighting",
abstract = "We present in this paper an approach to assessing student paraphrases in the intelligent tutoring system iSTART. The approach is based on measuring the semantic similarity between a student paraphrase and a reference text, called the textbase. The semantic similarity is estimated using knowledge-based word relatedness measures. The relatedness measures rely on knowledge encoded in Word-Net, a lexical database of English. We also experiment with weighting words based on their importance. The word importance information was derived from an analysis of word distributions in 2,225,726 documents from Wikipedia. Performance is reported for 12 different models which resulted from combining 3 different relatedness measures, 2 word sense disambiguation methods, and 2 word-weighting schemes. Furthermore, comparisons are made to other approaches such as Latent Semantic Analysis and the Entailer.",
keywords = "Intelligent tutoring systems, Natural language processing",
author = "Vasile Rus and Mihai Lintean and Art Graesser and Danielle McNamara",
year = "2009",
doi = "10.3233/978-1-60750-028-5-165",
language = "English (US)",
isbn = "9781607500285",
volume = "200",
series = "Frontiers in Artificial Intelligence and Applications",
number = "1",
pages = "165--172",
booktitle = "Frontiers in Artificial Intelligence and Applications",
edition = "1",

}

TY - GEN

T1 - Assessing student paraphrases using lexical semantics and word weighting

AU - Rus, Vasile

AU - Lintean, Mihai

AU - Graesser, Art

AU - McNamara, Danielle

PY - 2009

Y1 - 2009

N2 - We present in this paper an approach to assessing student paraphrases in the intelligent tutoring system iSTART. The approach is based on measuring the semantic similarity between a student paraphrase and a reference text, called the textbase. The semantic similarity is estimated using knowledge-based word relatedness measures. The relatedness measures rely on knowledge encoded in Word-Net, a lexical database of English. We also experiment with weighting words based on their importance. The word importance information was derived from an analysis of word distributions in 2,225,726 documents from Wikipedia. Performance is reported for 12 different models which resulted from combining 3 different relatedness measures, 2 word sense disambiguation methods, and 2 word-weighting schemes. Furthermore, comparisons are made to other approaches such as Latent Semantic Analysis and the Entailer.

AB - We present in this paper an approach to assessing student paraphrases in the intelligent tutoring system iSTART. The approach is based on measuring the semantic similarity between a student paraphrase and a reference text, called the textbase. The semantic similarity is estimated using knowledge-based word relatedness measures. The relatedness measures rely on knowledge encoded in Word-Net, a lexical database of English. We also experiment with weighting words based on their importance. The word importance information was derived from an analysis of word distributions in 2,225,726 documents from Wikipedia. Performance is reported for 12 different models which resulted from combining 3 different relatedness measures, 2 word sense disambiguation methods, and 2 word-weighting schemes. Furthermore, comparisons are made to other approaches such as Latent Semantic Analysis and the Entailer.

KW - Intelligent tutoring systems

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=73149114409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73149114409&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-028-5-165

DO - 10.3233/978-1-60750-028-5-165

M3 - Conference contribution

AN - SCOPUS:73149114409

SN - 9781607500285

VL - 200

T3 - Frontiers in Artificial Intelligence and Applications

SP - 165

EP - 172

BT - Frontiers in Artificial Intelligence and Applications

ER -