A linguistic analysis of expert-generated paraphrases

Russell D. Brandon, Scott A. Crossley, Danielle McNamara

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

Abstract

The authors used the computational tool Coh-Metrix to examine expert writers' paraphrases and in particular, how experts paraphrase text passages using condensing strategies. The overarching goal of this study was to develop machine learning algorithms to aid in the automatic detection of paraphrases and paraphrase types. To this end, three experts were instructed to paraphrase by condensing a set of target passages. The linguistic differences between the original passages and the condensed paraphrases were then analyzed using Coh-Metrix. The condensed paraphrases were accurately distinguished from the original target passages based on the number of words, word frequency, and syntactic complexity.

Original languageEnglish (US)
Title of host publicationProceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25
Pages268-271
Number of pages4
StatePublished - 2012
Event25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25 - Marco Island, FL, United States
Duration: May 23 2012May 25 2012

Other

Other25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25
CountryUnited States
CityMarco Island, FL
Period5/23/125/25/12

Fingerprint

Syntactics
Linguistics
Learning algorithms
Learning systems

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Brandon, R. D., Crossley, S. A., & McNamara, D. (2012). A linguistic analysis of expert-generated paraphrases. In Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25 (pp. 268-271)

A linguistic analysis of expert-generated paraphrases. / Brandon, Russell D.; Crossley, Scott A.; McNamara, Danielle.

Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25. 2012. p. 268-271.

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

Brandon, RD, Crossley, SA & McNamara, D 2012, A linguistic analysis of expert-generated paraphrases. in Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25. pp. 268-271, 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25, Marco Island, FL, United States, 5/23/12.
Brandon RD, Crossley SA, McNamara D. A linguistic analysis of expert-generated paraphrases. In Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25. 2012. p. 268-271
Brandon, Russell D. ; Crossley, Scott A. ; McNamara, Danielle. / A linguistic analysis of expert-generated paraphrases. Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25. 2012. pp. 268-271
@inproceedings{04b5f1133a0c46e9a25ccfe9f9368ef3,
title = "A linguistic analysis of expert-generated paraphrases",
abstract = "The authors used the computational tool Coh-Metrix to examine expert writers' paraphrases and in particular, how experts paraphrase text passages using condensing strategies. The overarching goal of this study was to develop machine learning algorithms to aid in the automatic detection of paraphrases and paraphrase types. To this end, three experts were instructed to paraphrase by condensing a set of target passages. The linguistic differences between the original passages and the condensed paraphrases were then analyzed using Coh-Metrix. The condensed paraphrases were accurately distinguished from the original target passages based on the number of words, word frequency, and syntactic complexity.",
author = "Brandon, {Russell D.} and Crossley, {Scott A.} and Danielle McNamara",
year = "2012",
language = "English (US)",
isbn = "9781577355588",
pages = "268--271",
booktitle = "Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25",

}

TY - GEN

T1 - A linguistic analysis of expert-generated paraphrases

AU - Brandon, Russell D.

AU - Crossley, Scott A.

AU - McNamara, Danielle

PY - 2012

Y1 - 2012

N2 - The authors used the computational tool Coh-Metrix to examine expert writers' paraphrases and in particular, how experts paraphrase text passages using condensing strategies. The overarching goal of this study was to develop machine learning algorithms to aid in the automatic detection of paraphrases and paraphrase types. To this end, three experts were instructed to paraphrase by condensing a set of target passages. The linguistic differences between the original passages and the condensed paraphrases were then analyzed using Coh-Metrix. The condensed paraphrases were accurately distinguished from the original target passages based on the number of words, word frequency, and syntactic complexity.

AB - The authors used the computational tool Coh-Metrix to examine expert writers' paraphrases and in particular, how experts paraphrase text passages using condensing strategies. The overarching goal of this study was to develop machine learning algorithms to aid in the automatic detection of paraphrases and paraphrase types. To this end, three experts were instructed to paraphrase by condensing a set of target passages. The linguistic differences between the original passages and the condensed paraphrases were then analyzed using Coh-Metrix. The condensed paraphrases were accurately distinguished from the original target passages based on the number of words, word frequency, and syntactic complexity.

UR - http://www.scopus.com/inward/record.url?scp=84864986745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864986745&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84864986745

SN - 9781577355588

SP - 268

EP - 271

BT - Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25

ER -