@inproceedings{vajjala-banerjee-2017-study,
title = "A study of N-gram and Embedding Representations for Native Language Identification",
author = "Vajjala, Sowmya and
Banerjee, Sagnik",
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/W17-5026",
doi = "10.18653/v1/W17-5026",
pages = "240--248",
abstract = "We report on our experiments with N-gram and embedding based feature representations for Native Language Identification (NLI) as a part of the NLI Shared Task 2017 (team name: NLI-ISU). Our best performing system on the test set for written essays had a macro F1 of 0.8264 and was based on word uni, bi and trigram features. We explored n-grams covering word, character, POS and word-POS mixed representations for this task. For embedding based feature representations, we employed both word and document embeddings. We had a relatively poor performance with all embedding representations compared to n-grams, which could be because of the fact that embeddings capture semantic similarities whereas L1 differences are more stylistic in nature.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vajjala-banerjee-2017-study">
<titleInfo>
<title>A study of N-gram and Embedding Representations for Native Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">Vajjala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sagnik</namePart>
<namePart type="family">Banerjee</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 report on our experiments with N-gram and embedding based feature representations for Native Language Identification (NLI) as a part of the NLI Shared Task 2017 (team name: NLI-ISU). Our best performing system on the test set for written essays had a macro F1 of 0.8264 and was based on word uni, bi and trigram features. We explored n-grams covering word, character, POS and word-POS mixed representations for this task. For embedding based feature representations, we employed both word and document embeddings. We had a relatively poor performance with all embedding representations compared to n-grams, which could be because of the fact that embeddings capture semantic similarities whereas L1 differences are more stylistic in nature.</abstract>
<identifier type="citekey">vajjala-banerjee-2017-study</identifier>
<identifier type="doi">10.18653/v1/W17-5026</identifier>
<location>
<url>https://aclanthology.org/W17-5026</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>240</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A study of N-gram and Embedding Representations for Native Language Identification
%A Vajjala, Sowmya
%A Banerjee, Sagnik
%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 vajjala-banerjee-2017-study
%X We report on our experiments with N-gram and embedding based feature representations for Native Language Identification (NLI) as a part of the NLI Shared Task 2017 (team name: NLI-ISU). Our best performing system on the test set for written essays had a macro F1 of 0.8264 and was based on word uni, bi and trigram features. We explored n-grams covering word, character, POS and word-POS mixed representations for this task. For embedding based feature representations, we employed both word and document embeddings. We had a relatively poor performance with all embedding representations compared to n-grams, which could be because of the fact that embeddings capture semantic similarities whereas L1 differences are more stylistic in nature.
%R 10.18653/v1/W17-5026
%U https://aclanthology.org/W17-5026
%U https://doi.org/10.18653/v1/W17-5026
%P 240-248
Markdown (Informal)
[A study of N-gram and Embedding Representations for Native Language Identification](https://aclanthology.org/W17-5026) (Vajjala & Banerjee, BEA 2017)
ACL