@inproceedings{markov-etal-2017-cic,
title = "{CIC}-{FBK} Approach to Native Language Identification",
author = "Markov, Ilia and
Chen, Lingzhen and
Strapparava, Carlo and
Sidorov, Grigori",
editor = "Tetreault, Joel and
Burstein, Jill and
Leacock, Claudia and
Yannakoudakis, Helen",
booktitle = "Proceedings of the 12th Workshop on Innovative Use of {NLP} for Building Educational Applications",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-5042",
doi = "10.18653/v1/W17-5042",
pages = "374--381",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="markov-etal-2017-cic">
<titleInfo>
<title>CIC-FBK Approach to Native Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilia</namePart>
<namePart type="family">Markov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingzhen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Strapparava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">markov-etal-2017-cic</identifier>
<identifier type="doi">10.18653/v1/W17-5042</identifier>
<location>
<url>https://aclanthology.org/W17-5042</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>374</start>
<end>381</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIC-FBK Approach to Native Language Identification
%A Markov, Ilia
%A Chen, Lingzhen
%A Strapparava, Carlo
%A Sidorov, Grigori
%Y Tetreault, Joel
%Y Burstein, Jill
%Y Leacock, Claudia
%Y Yannakoudakis, Helen
%S Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F markov-etal-2017-cic
%X 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.
%R 10.18653/v1/W17-5042
%U https://aclanthology.org/W17-5042
%U https://doi.org/10.18653/v1/W17-5042
%P 374-381
Markdown (Informal)
[CIC-FBK Approach to Native Language Identification](https://aclanthology.org/W17-5042) (Markov et al., BEA 2017)
ACL
- Ilia Markov, Lingzhen Chen, Carlo Strapparava, and Grigori Sidorov. 2017. CIC-FBK Approach to Native Language Identification. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 374–381, Copenhagen, Denmark. Association for Computational Linguistics.