@inproceedings{ferrero-etal-2017-using,
title = "Using Word Embedding for Cross-Language Plagiarism Detection",
author = "Ferrero, J{\'e}r{\'e}my and
Besacier, Laurent and
Schwab, Didier and
Agn{\`e}s, Fr{\'e}d{\'e}ric",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2066",
pages = "415--421",
abstract = "This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection. The main contributions of this paper are the following: (a) we introduce new cross-language similarity detection methods based on distributed representation of words; (b) we combine the different methods proposed to verify their complementarity and finally obtain an overall F1 score of 89.15{\%} for English-French similarity detection at chunk level (88.5{\%} at sentence level) on a very challenging corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrero-etal-2017-using">
<titleInfo>
<title>Using Word Embedding for Cross-Language Plagiarism Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jérémy</namePart>
<namePart type="family">Ferrero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Didier</namePart>
<namePart type="family">Schwab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Agnès</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection. The main contributions of this paper are the following: (a) we introduce new cross-language similarity detection methods based on distributed representation of words; (b) we combine the different methods proposed to verify their complementarity and finally obtain an overall F1 score of 89.15% for English-French similarity detection at chunk level (88.5% at sentence level) on a very challenging corpus.</abstract>
<identifier type="citekey">ferrero-etal-2017-using</identifier>
<location>
<url>https://aclanthology.org/E17-2066</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>415</start>
<end>421</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Word Embedding for Cross-Language Plagiarism Detection
%A Ferrero, Jérémy
%A Besacier, Laurent
%A Schwab, Didier
%A Agnès, Frédéric
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F ferrero-etal-2017-using
%X This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection. The main contributions of this paper are the following: (a) we introduce new cross-language similarity detection methods based on distributed representation of words; (b) we combine the different methods proposed to verify their complementarity and finally obtain an overall F1 score of 89.15% for English-French similarity detection at chunk level (88.5% at sentence level) on a very challenging corpus.
%U https://aclanthology.org/E17-2066
%P 415-421
Markdown (Informal)
[Using Word Embedding for Cross-Language Plagiarism Detection](https://aclanthology.org/E17-2066) (Ferrero et al., EACL 2017)
ACL
- Jérémy Ferrero, Laurent Besacier, Didier Schwab, and Frédéric Agnès. 2017. Using Word Embedding for Cross-Language Plagiarism Detection. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 415–421, Valencia, Spain. Association for Computational Linguistics.