@inproceedings{sharaf-atwell-2012-qursim,
title = "{Q}ur{S}im: A corpus for evaluation of relatedness in short texts",
author = "Sharaf, Abdul-Baquee and
Atwell, Eric",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/190_Paper.pdf",
pages = "2295--2302",
abstract = "This paper presents a large corpus created from the original Quranic text, where semantically similar or related verses are linked together. This corpus will be a valuable evaluation resource for computational linguists investigating similarity and relatedness in short texts. Furthermore, this dataset can be used for evaluation of paraphrase analysis and machine translation tasks. Our dataset is characterised by: (1) superior quality of relatedness assignment; as we have incorporated relations marked by well-known domain experts, this dataset could thus be considered a gold standard corpus for various evaluation tasks, (2) the size of our dataset; over 7,600 pairs of related verses are collected from scholarly sources with several levels of degree of relatedness. This dataset could be extended to over 13,500 pairs of related verses observing the commutative property of strongly related pairs. This dataset was incorporated into online query pages where users can visualize for a given verse a network of all directly and indirectly related verses. Empirical experiments showed that only 33{\%} of related pairs shared root words, emphasising the need to go beyond common lexical matching methods, and incorporate -in addition- semantic, domain knowledge, and other corpus-based approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharaf-atwell-2012-qursim">
<titleInfo>
<title>QurSim: A corpus for evaluation of relatedness in short texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdul-Baquee</namePart>
<namePart type="family">Sharaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a large corpus created from the original Quranic text, where semantically similar or related verses are linked together. This corpus will be a valuable evaluation resource for computational linguists investigating similarity and relatedness in short texts. Furthermore, this dataset can be used for evaluation of paraphrase analysis and machine translation tasks. Our dataset is characterised by: (1) superior quality of relatedness assignment; as we have incorporated relations marked by well-known domain experts, this dataset could thus be considered a gold standard corpus for various evaluation tasks, (2) the size of our dataset; over 7,600 pairs of related verses are collected from scholarly sources with several levels of degree of relatedness. This dataset could be extended to over 13,500 pairs of related verses observing the commutative property of strongly related pairs. This dataset was incorporated into online query pages where users can visualize for a given verse a network of all directly and indirectly related verses. Empirical experiments showed that only 33% of related pairs shared root words, emphasising the need to go beyond common lexical matching methods, and incorporate -in addition- semantic, domain knowledge, and other corpus-based approaches.</abstract>
<identifier type="citekey">sharaf-atwell-2012-qursim</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/190_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2295</start>
<end>2302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QurSim: A corpus for evaluation of relatedness in short texts
%A Sharaf, Abdul-Baquee
%A Atwell, Eric
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F sharaf-atwell-2012-qursim
%X This paper presents a large corpus created from the original Quranic text, where semantically similar or related verses are linked together. This corpus will be a valuable evaluation resource for computational linguists investigating similarity and relatedness in short texts. Furthermore, this dataset can be used for evaluation of paraphrase analysis and machine translation tasks. Our dataset is characterised by: (1) superior quality of relatedness assignment; as we have incorporated relations marked by well-known domain experts, this dataset could thus be considered a gold standard corpus for various evaluation tasks, (2) the size of our dataset; over 7,600 pairs of related verses are collected from scholarly sources with several levels of degree of relatedness. This dataset could be extended to over 13,500 pairs of related verses observing the commutative property of strongly related pairs. This dataset was incorporated into online query pages where users can visualize for a given verse a network of all directly and indirectly related verses. Empirical experiments showed that only 33% of related pairs shared root words, emphasising the need to go beyond common lexical matching methods, and incorporate -in addition- semantic, domain knowledge, and other corpus-based approaches.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/190_Paper.pdf
%P 2295-2302
Markdown (Informal)
[QurSim: A corpus for evaluation of relatedness in short texts](http://www.lrec-conf.org/proceedings/lrec2012/pdf/190_Paper.pdf) (Sharaf & Atwell, LREC 2012)
ACL