@inproceedings{sharjeel-etal-2016-uppc,
title = "{UPPC} - {U}rdu Paraphrase Plagiarism Corpus",
author = "Sharjeel, Muhammad and
Rayson, Paul and
Nawab, Rao Muhammad Adeel",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1289",
pages = "1832--1836",
abstract = "Paraphrase plagiarism is a significant and widespread problem and research shows that it is hard to detect. Several methods and automatic systems have been proposed to deal with it. However, evaluation and comparison of such solutions is not possible because of the unavailability of benchmark corpora with manual examples of paraphrase plagiarism. To deal with this issue, we present the novel development of a paraphrase plagiarism corpus containing simulated (manually created) examples in the Urdu language - a language widely spoken around the world. This resource is the first of its kind developed for the Urdu language and we believe that it will be a valuable contribution to the evaluation of paraphrase plagiarism detection systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharjeel-etal-2016-uppc">
<titleInfo>
<title>UPPC - Urdu Paraphrase Plagiarism Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Sharjeel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rao</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="given">Adeel</namePart>
<namePart type="family">Nawab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrase plagiarism is a significant and widespread problem and research shows that it is hard to detect. Several methods and automatic systems have been proposed to deal with it. However, evaluation and comparison of such solutions is not possible because of the unavailability of benchmark corpora with manual examples of paraphrase plagiarism. To deal with this issue, we present the novel development of a paraphrase plagiarism corpus containing simulated (manually created) examples in the Urdu language - a language widely spoken around the world. This resource is the first of its kind developed for the Urdu language and we believe that it will be a valuable contribution to the evaluation of paraphrase plagiarism detection systems.</abstract>
<identifier type="citekey">sharjeel-etal-2016-uppc</identifier>
<location>
<url>https://aclanthology.org/L16-1289</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1832</start>
<end>1836</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPPC - Urdu Paraphrase Plagiarism Corpus
%A Sharjeel, Muhammad
%A Rayson, Paul
%A Nawab, Rao Muhammad Adeel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F sharjeel-etal-2016-uppc
%X Paraphrase plagiarism is a significant and widespread problem and research shows that it is hard to detect. Several methods and automatic systems have been proposed to deal with it. However, evaluation and comparison of such solutions is not possible because of the unavailability of benchmark corpora with manual examples of paraphrase plagiarism. To deal with this issue, we present the novel development of a paraphrase plagiarism corpus containing simulated (manually created) examples in the Urdu language - a language widely spoken around the world. This resource is the first of its kind developed for the Urdu language and we believe that it will be a valuable contribution to the evaluation of paraphrase plagiarism detection systems.
%U https://aclanthology.org/L16-1289
%P 1832-1836
Markdown (Informal)
[UPPC - Urdu Paraphrase Plagiarism Corpus](https://aclanthology.org/L16-1289) (Sharjeel et al., LREC 2016)
ACL
- Muhammad Sharjeel, Paul Rayson, and Rao Muhammad Adeel Nawab. 2016. UPPC - Urdu Paraphrase Plagiarism Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1832–1836, Portorož, Slovenia. European Language Resources Association (ELRA).