Cic-fbk approach to native language identification

Ilia Markov; Lingzhen Chen; Carlo Strapparava; Grigori Sidorov

Cic-fbk approach to native language identification

Ilia Markov, Lingzhen Chen, Carlo Strapparava, Grigori Sidorov

Centro de Investigación en Computación (CIC)

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

17 Scopus citations

Abstract

We present the CIC-FBK system, which took part in the Native Language Identification (NLI) Shared Task 2017. Our approach combines features commonly used in previous NLI research, i.e., word n-grams, lemma n-grams, part-of-speech n-grams, and function words, with recently introduced character n-grams from misspelled words, and features that are novel in this task, such as typed character n-grams, and syntactic n-grams of words and of syntactic relation tags. We use log-entropy weighting scheme and perform classification using the Support Vector Machines (SVM) algorithm. Our system achieved 0.8808 macro-averaged F1-score and shared the 1st rank in the NLI Shared Task 2017 scoring.

Original language	English
Title of host publication	EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	374-381
Number of pages	8
ISBN (Electronic)	9781945626852
State	Published - 2017
Event	12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017, held in conjunction with EMNLP 2017 - Copenhagen, Denmark Duration: 8 Sep 2017 → …

Publication series

Name	EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop

Conference

Conference	12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017, held in conjunction with EMNLP 2017
Country/Territory	Denmark
City	Copenhagen
Period	8/09/17 → …

Cite this

Markov, I., Chen, L., Strapparava, C., & Sidorov, G. (2017). Cic-fbk approach to native language identification. In EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop (pp. 374-381). (EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop). Association for Computational Linguistics (ACL).

Markov, Ilia ; Chen, Lingzhen ; Strapparava, Carlo et al. / Cic-fbk approach to native language identification. EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. pp. 374-381 (EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop).

@inproceedings{59096b50dd804ebbb3c17fb407ef6a64,

title = "Cic-fbk approach to native language identification",

abstract = "We present the CIC-FBK system, which took part in the Native Language Identification (NLI) Shared Task 2017. Our approach combines features commonly used in previous NLI research, i.e., word n-grams, lemma n-grams, part-of-speech n-grams, and function words, with recently introduced character n-grams from misspelled words, and features that are novel in this task, such as typed character n-grams, and syntactic n-grams of words and of syntactic relation tags. We use log-entropy weighting scheme and perform classification using the Support Vector Machines (SVM) algorithm. Our system achieved 0.8808 macro-averaged F1-score and shared the 1st rank in the NLI Shared Task 2017 scoring.",

author = "Ilia Markov and Lingzhen Chen and Carlo Strapparava and Grigori Sidorov",

note = "Publisher Copyright: {\textcopyright} EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop. All rights reserved.; 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017, held in conjunction with EMNLP 2017 ; Conference date: 08-09-2017",

year = "2017",

language = "Ingl{\'e}s",

series = "EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop",

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

pages = "374--381",

booktitle = "EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop",

}

Markov, I, Chen, L, Strapparava, C & Sidorov, G 2017, Cic-fbk approach to native language identification. in EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop. EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 374-381, 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017, held in conjunction with EMNLP 2017, Copenhagen, Denmark, 8/09/17.

Cic-fbk approach to native language identification. / Markov, Ilia; Chen, Lingzhen; Strapparava, Carlo et al.
EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. p. 374-381 (EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop).

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

TY - GEN

T1 - Cic-fbk approach to native language identification

AU - Markov, Ilia

AU - Chen, Lingzhen

AU - Strapparava, Carlo

AU - Sidorov, Grigori

PY - 2017

Y1 - 2017

N2 - We present the CIC-FBK system, which took part in the Native Language Identification (NLI) Shared Task 2017. Our approach combines features commonly used in previous NLI research, i.e., word n-grams, lemma n-grams, part-of-speech n-grams, and function words, with recently introduced character n-grams from misspelled words, and features that are novel in this task, such as typed character n-grams, and syntactic n-grams of words and of syntactic relation tags. We use log-entropy weighting scheme and perform classification using the Support Vector Machines (SVM) algorithm. Our system achieved 0.8808 macro-averaged F1-score and shared the 1st rank in the NLI Shared Task 2017 scoring.

AB - We present the CIC-FBK system, which took part in the Native Language Identification (NLI) Shared Task 2017. Our approach combines features commonly used in previous NLI research, i.e., word n-grams, lemma n-grams, part-of-speech n-grams, and function words, with recently introduced character n-grams from misspelled words, and features that are novel in this task, such as typed character n-grams, and syntactic n-grams of words and of syntactic relation tags. We use log-entropy weighting scheme and perform classification using the Support Vector Machines (SVM) algorithm. Our system achieved 0.8808 macro-averaged F1-score and shared the 1st rank in the NLI Shared Task 2017 scoring.

UR - http://www.scopus.com/inward/record.url?scp=85096916226&partnerID=8YFLogxK

M3 - Contribución a la conferencia

AN - SCOPUS:85096916226

T3 - EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop

SP - 374

EP - 381

BT - EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

T2 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017, held in conjunction with EMNLP 2017

Y2 - 8 September 2017

ER -

Markov I, Chen L, Strapparava C, Sidorov G. Cic-fbk approach to native language identification. In EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2017. p. 374-381. (EMNLP 2017 - 12th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2017 - Proceedings of the Workshop).

Cic-fbk approach to native language identification

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this