@inproceedings{humayoun-etal-2016-urdu,
title = "{U}rdu Summary Corpus",
author = "Humayoun, Muhammad and
Nawab, Rao Muhammad Adeel and
Uzair, Muhammad and
Aslam, Saba and
Farzand, Omer",
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/L16-1128",
pages = "796--800",
abstract = "Language resources, such as corpora, are important for various natural language processing tasks. Urdu has millions of speakers around the world but it is under-resourced in terms of standard evaluation resources. This paper reports the construction of a benchmark corpus for Urdu summaries (abstracts) to facilitate the development and evaluation of single document summarization systems for Urdu language. In Urdu, space does not always mark word boundary. Therefore, we created two versions of the same corpus. In the first version, words are separated by space. In contrast, proper word boundaries are manually tagged in the second version. We further apply normalization, part-of-speech tagging, morphological analysis, lemmatization, and stemming for the articles and their summaries in both versions. In order to apply these annotations, we re-implemented some NLP tools for Urdu. We provide Urdu Summary Corpus, all these annotations and the needed software tools (as open-source) for researchers to run experiments and to evaluate their work including but not limited to single-document summarization task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="humayoun-etal-2016-urdu">
<titleInfo>
<title>Urdu Summary Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Humayoun</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>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Uzair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Aslam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Farzand</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>Language resources, such as corpora, are important for various natural language processing tasks. Urdu has millions of speakers around the world but it is under-resourced in terms of standard evaluation resources. This paper reports the construction of a benchmark corpus for Urdu summaries (abstracts) to facilitate the development and evaluation of single document summarization systems for Urdu language. In Urdu, space does not always mark word boundary. Therefore, we created two versions of the same corpus. In the first version, words are separated by space. In contrast, proper word boundaries are manually tagged in the second version. We further apply normalization, part-of-speech tagging, morphological analysis, lemmatization, and stemming for the articles and their summaries in both versions. In order to apply these annotations, we re-implemented some NLP tools for Urdu. We provide Urdu Summary Corpus, all these annotations and the needed software tools (as open-source) for researchers to run experiments and to evaluate their work including but not limited to single-document summarization task.</abstract>
<identifier type="citekey">humayoun-etal-2016-urdu</identifier>
<location>
<url>https://aclanthology.org/L16-1128</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>796</start>
<end>800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Urdu Summary Corpus
%A Humayoun, Muhammad
%A Nawab, Rao Muhammad Adeel
%A Uzair, Muhammad
%A Aslam, Saba
%A Farzand, Omer
%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 humayoun-etal-2016-urdu
%X Language resources, such as corpora, are important for various natural language processing tasks. Urdu has millions of speakers around the world but it is under-resourced in terms of standard evaluation resources. This paper reports the construction of a benchmark corpus for Urdu summaries (abstracts) to facilitate the development and evaluation of single document summarization systems for Urdu language. In Urdu, space does not always mark word boundary. Therefore, we created two versions of the same corpus. In the first version, words are separated by space. In contrast, proper word boundaries are manually tagged in the second version. We further apply normalization, part-of-speech tagging, morphological analysis, lemmatization, and stemming for the articles and their summaries in both versions. In order to apply these annotations, we re-implemented some NLP tools for Urdu. We provide Urdu Summary Corpus, all these annotations and the needed software tools (as open-source) for researchers to run experiments and to evaluate their work including but not limited to single-document summarization task.
%U https://aclanthology.org/L16-1128
%P 796-800
Markdown (Informal)
[Urdu Summary Corpus](https://aclanthology.org/L16-1128) (Humayoun et al., LREC 2016)
ACL
- Muhammad Humayoun, Rao Muhammad Adeel Nawab, Muhammad Uzair, Saba Aslam, and Omer Farzand. 2016. Urdu Summary Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 796–800, Portorož, Slovenia. European Language Resources Association (ELRA).