Native Language Identification: A Key N-gram Category Approach

Kristopher Kyle; Scott Crossley; Jianmin Dai; Danielle S. McNamara

Native Language Identification: A Key N-gram Category Approach

Kristopher Kyle, Scott Crossley, Jianmin Dai, Danielle S. McNamara

Department of English Language and Literature

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

2 Citations (Scopus)

Abstract

This study explores the efficacy of an approach to native language identification that utilizes grammatical, rhetorical, semantic, syntactic, and cohesive function categories comprised of key n-grams. The study found that a model based on these categories of key n-grams was able to successfully predict the L1 of essays written in English by L2 learners from 11 different L1 backgrounds with an accuracy of 59%. Preliminary findings concerning instances of crosslinguistic influence are discussed, along with evidence of language similarities based on patterns of language misclassification.

Original language	English
Title of host publication	Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013
Editors	Joel Tetreault, Jill Burstein, Claudia Leacock
Publisher	Association for Computational Linguistics (ACL)
Pages	242-250
Number of pages	9
ISBN (Electronic)	9781937284473
Publication status	Published - 2013
Event	8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013 - Atlanta, United States Duration: 2013 Jun 13 → …

Publication series

Name	Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013

Conference

Conference	8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013
Country/Territory	United States
City	Atlanta
Period	13/6/13 → …

Bibliographical note

Publisher Copyright:
© 2013 Association for Computational Linguistics.

All Science Journal Classification (ASJC) codes

Computer Science Applications
Information Systems
Computational Theory and Mathematics

Cite this

Kyle, K., Crossley, S., Dai, J., & McNamara, D. S. (2013). Native Language Identification: A Key N-gram Category Approach. In J. Tetreault, J. Burstein, & C. Leacock (Eds.), Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013 (pp. 242-250). (Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013). Association for Computational Linguistics (ACL).

Kyle, Kristopher ; Crossley, Scott ; Dai, Jianmin et al. / Native Language Identification : A Key N-gram Category Approach. Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013. editor / Joel Tetreault ; Jill Burstein ; Claudia Leacock. Association for Computational Linguistics (ACL), 2013. pp. 242-250 (Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013).

@inproceedings{f08d0705d48f40c48ccbff99854f7f4a,

title = "Native Language Identification: A Key N-gram Category Approach",

abstract = "This study explores the efficacy of an approach to native language identification that utilizes grammatical, rhetorical, semantic, syntactic, and cohesive function categories comprised of key n-grams. The study found that a model based on these categories of key n-grams was able to successfully predict the L1 of essays written in English by L2 learners from 11 different L1 backgrounds with an accuracy of 59%. Preliminary findings concerning instances of crosslinguistic influence are discussed, along with evidence of language similarities based on patterns of language misclassification.",

author = "Kristopher Kyle and Scott Crossley and Jianmin Dai and McNamara, {Danielle S.}",

note = "Publisher Copyright: {\textcopyright} 2013 Association for Computational Linguistics.; 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013 ; Conference date: 13-06-2013",

year = "2013",

language = "English",

series = "Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013",

publisher = "Association for Computational Linguistics (ACL)",

pages = "242--250",

editor = "Joel Tetreault and Jill Burstein and Claudia Leacock",

booktitle = "Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013",

}

Kyle, K, Crossley, S, Dai, J & McNamara, DS 2013, Native Language Identification: A Key N-gram Category Approach. in J Tetreault, J Burstein & C Leacock (eds), Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013. Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013, Association for Computational Linguistics (ACL), pp. 242-250, 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013, Atlanta, United States, 13/6/13.

Native Language Identification: A Key N-gram Category Approach. / Kyle, Kristopher; Crossley, Scott; Dai, Jianmin et al.
Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013. ed. / Joel Tetreault; Jill Burstein; Claudia Leacock. Association for Computational Linguistics (ACL), 2013. p. 242-250 (Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013).

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

TY - GEN

T1 - Native Language Identification

T2 - 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013

AU - Kyle, Kristopher

AU - Crossley, Scott

AU - Dai, Jianmin

AU - McNamara, Danielle S.

PY - 2013

Y1 - 2013

N2 - This study explores the efficacy of an approach to native language identification that utilizes grammatical, rhetorical, semantic, syntactic, and cohesive function categories comprised of key n-grams. The study found that a model based on these categories of key n-grams was able to successfully predict the L1 of essays written in English by L2 learners from 11 different L1 backgrounds with an accuracy of 59%. Preliminary findings concerning instances of crosslinguistic influence are discussed, along with evidence of language similarities based on patterns of language misclassification.

AB - This study explores the efficacy of an approach to native language identification that utilizes grammatical, rhetorical, semantic, syntactic, and cohesive function categories comprised of key n-grams. The study found that a model based on these categories of key n-grams was able to successfully predict the L1 of essays written in English by L2 learners from 11 different L1 backgrounds with an accuracy of 59%. Preliminary findings concerning instances of crosslinguistic influence are discussed, along with evidence of language similarities based on patterns of language misclassification.

UR - http://www.scopus.com/inward/record.url?scp=84958080733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958080733&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84958080733

T3 - Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013

SP - 242

EP - 250

BT - Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013

A2 - Tetreault, Joel

A2 - Burstein, Jill

A2 - Leacock, Claudia

PB - Association for Computational Linguistics (ACL)

Y2 - 13 June 2013

ER -

Kyle K, Crossley S, Dai J, McNamara DS. Native Language Identification: A Key N-gram Category Approach. In Tetreault J, Burstein J, Leacock C, editors, Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013. Association for Computational Linguistics (ACL). 2013. p. 242-250. (Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013).

Native Language Identification: A Key N-gram Category Approach

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this