Large-scale Native Language Identification with cross-corpus evaluation

Shervin Malmasi; Mark Dras

doi:10.3115/v1/n15-1160

Large-scale Native Language Identification with cross-corpus evaluation

Shervin Malmasi, Mark Dras

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

25 Citations (Scopus)

Abstract

We present a large-scale Native Language Identification (NLI) experiment on new data, with a focus on cross-corpus evaluation to identify corpus- and genre-independent language transfer features. We test a new corpus and show it is comparable to other NLI corpora and suitable for this task. Cross-corpus evaluation on two large corpora achieves good accuracy and evidences the existence of reliable language transfer features, but lower performance also suggests that NLI models are not completely portable across corpora. Finally, we present a brief case study of features distinguishing Japanese learners' English writing, demonstrating the presence of cross-corpus and cross-genre language transfer features that are highly applicable to SLA and ESL research.

Original language	English
Title of host publication	2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
Subtitle of host publication	Proceedings of the Conference
Place of Publication	Red Hook, NY
Publisher	Association for Computational Linguistics (ACL)
Pages	1403-1409
Number of pages	7
ISBN (Electronic)	9781941643495
DOIs	https://doi.org/10.3115/v1/n15-1160
Publication status	Published - 2015
Event	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States Duration: 31 May 2015 → 5 Jun 2015

Other

Other	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
Country/Territory	United States
City	Denver
Period	31/05/15 → 5/06/15

Access to Document

10.3115/v1/n15-1160

Cite this

Malmasi, S., & Dras, M. (2015). Large-scale Native Language Identification with cross-corpus evaluation. In 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015: Proceedings of the Conference (pp. 1403-1409). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/n15-1160

@inproceedings{fd5514ec0d1e4b4a9a4a6f62ddc7c165,

title = "Large-scale Native Language Identification with cross-corpus evaluation",

abstract = "We present a large-scale Native Language Identification (NLI) experiment on new data, with a focus on cross-corpus evaluation to identify corpus- and genre-independent language transfer features. We test a new corpus and show it is comparable to other NLI corpora and suitable for this task. Cross-corpus evaluation on two large corpora achieves good accuracy and evidences the existence of reliable language transfer features, but lower performance also suggests that NLI models are not completely portable across corpora. Finally, we present a brief case study of features distinguishing Japanese learners' English writing, demonstrating the presence of cross-corpus and cross-genre language transfer features that are highly applicable to SLA and ESL research.",

author = "Shervin Malmasi and Mark Dras",

year = "2015",

doi = "10.3115/v1/n15-1160",

language = "English",

pages = "1403--1409",

booktitle = "2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015",

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

note = "Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 ; Conference date: 31-05-2015 Through 05-06-2015",

}

Malmasi, S & Dras, M 2015, Large-scale Native Language Identification with cross-corpus evaluation. in 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015: Proceedings of the Conference. Association for Computational Linguistics (ACL), Red Hook, NY, pp. 1403-1409, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, Denver, United States, 31/05/15. https://doi.org/10.3115/v1/n15-1160

Large-scale Native Language Identification with cross-corpus evaluation. / Malmasi, Shervin ; Dras, Mark.
2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015: Proceedings of the Conference. Red Hook, NY: Association for Computational Linguistics (ACL), 2015. p. 1403-1409.

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

TY - GEN

T1 - Large-scale Native Language Identification with cross-corpus evaluation

AU - Malmasi, Shervin

AU - Dras, Mark

PY - 2015

Y1 - 2015

N2 - We present a large-scale Native Language Identification (NLI) experiment on new data, with a focus on cross-corpus evaluation to identify corpus- and genre-independent language transfer features. We test a new corpus and show it is comparable to other NLI corpora and suitable for this task. Cross-corpus evaluation on two large corpora achieves good accuracy and evidences the existence of reliable language transfer features, but lower performance also suggests that NLI models are not completely portable across corpora. Finally, we present a brief case study of features distinguishing Japanese learners' English writing, demonstrating the presence of cross-corpus and cross-genre language transfer features that are highly applicable to SLA and ESL research.

AB - We present a large-scale Native Language Identification (NLI) experiment on new data, with a focus on cross-corpus evaluation to identify corpus- and genre-independent language transfer features. We test a new corpus and show it is comparable to other NLI corpora and suitable for this task. Cross-corpus evaluation on two large corpora achieves good accuracy and evidences the existence of reliable language transfer features, but lower performance also suggests that NLI models are not completely portable across corpora. Finally, we present a brief case study of features distinguishing Japanese learners' English writing, demonstrating the presence of cross-corpus and cross-genre language transfer features that are highly applicable to SLA and ESL research.

UR - http://www.scopus.com/inward/record.url?scp=84960157803&partnerID=8YFLogxK

U2 - 10.3115/v1/n15-1160

DO - 10.3115/v1/n15-1160

M3 - Conference proceeding contribution

AN - SCOPUS:84960157803

SP - 1403

EP - 1409

BT - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015

PB - Association for Computational Linguistics (ACL)

CY - Red Hook, NY

T2 - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015

Y2 - 31 May 2015 through 5 June 2015

ER -

Malmasi S , Dras M. Large-scale Native Language Identification with cross-corpus evaluation. In 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015: Proceedings of the Conference. Red Hook, NY: Association for Computational Linguistics (ACL). 2015. p. 1403-1409 doi: 10.3115/v1/n15-1160

Large-scale Native Language Identification with cross-corpus evaluation

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this