@inproceedings{seraji-etal-2012-basic,
title = "A Basic Language Resource Kit for {P}ersian",
author = "Seraji, Mojgan and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
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/338_Paper.pdf",
pages = "2245--2252",
abstract = "Persian with its about 100,000,000 speakers in the world belongs to the group of languages with less developed linguistically annotated resources and tools. The few existing resources and tools are neither open source nor freely available. Thus, our goal is to develop open source resources such as corpora and treebanks, and tools for data-driven linguistic analysis of Persian. We do this by exploring the reusability of existing resources and adapting state-of-the-art methods for the linguistic annotation. We present fully functional tools for text normalization, sentence segmentation, tokenization, part-of-speech tagging, and parsing. As for resources, we describe the Uppsala PErsian Corpus (UPEC) which is a modified version of the Bijankhan corpus with additional sentence segmentation and consistent tokenization modified for more appropriate syntactic annotation. The corpus consists of 2,782,109 tokens and is annotated with parts of speech and morphological features. A treebank is derived from UPEC with an annotation scheme based on Stanford Typed Dependencies and is planned to consist of 10,000 sentences of which 215 have already been annotated. Keywords: BLARK for Persian, PoS tagged corpus, Persian treebank",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seraji-etal-2012-basic">
<titleInfo>
<title>A Basic Language Resource Kit for Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mojgan</namePart>
<namePart type="family">Seraji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</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>Persian with its about 100,000,000 speakers in the world belongs to the group of languages with less developed linguistically annotated resources and tools. The few existing resources and tools are neither open source nor freely available. Thus, our goal is to develop open source resources such as corpora and treebanks, and tools for data-driven linguistic analysis of Persian. We do this by exploring the reusability of existing resources and adapting state-of-the-art methods for the linguistic annotation. We present fully functional tools for text normalization, sentence segmentation, tokenization, part-of-speech tagging, and parsing. As for resources, we describe the Uppsala PErsian Corpus (UPEC) which is a modified version of the Bijankhan corpus with additional sentence segmentation and consistent tokenization modified for more appropriate syntactic annotation. The corpus consists of 2,782,109 tokens and is annotated with parts of speech and morphological features. A treebank is derived from UPEC with an annotation scheme based on Stanford Typed Dependencies and is planned to consist of 10,000 sentences of which 215 have already been annotated. Keywords: BLARK for Persian, PoS tagged corpus, Persian treebank</abstract>
<identifier type="citekey">seraji-etal-2012-basic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/338_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2245</start>
<end>2252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Basic Language Resource Kit for Persian
%A Seraji, Mojgan
%A Megyesi, Beáta
%A Nivre, Joakim
%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 seraji-etal-2012-basic
%X Persian with its about 100,000,000 speakers in the world belongs to the group of languages with less developed linguistically annotated resources and tools. The few existing resources and tools are neither open source nor freely available. Thus, our goal is to develop open source resources such as corpora and treebanks, and tools for data-driven linguistic analysis of Persian. We do this by exploring the reusability of existing resources and adapting state-of-the-art methods for the linguistic annotation. We present fully functional tools for text normalization, sentence segmentation, tokenization, part-of-speech tagging, and parsing. As for resources, we describe the Uppsala PErsian Corpus (UPEC) which is a modified version of the Bijankhan corpus with additional sentence segmentation and consistent tokenization modified for more appropriate syntactic annotation. The corpus consists of 2,782,109 tokens and is annotated with parts of speech and morphological features. A treebank is derived from UPEC with an annotation scheme based on Stanford Typed Dependencies and is planned to consist of 10,000 sentences of which 215 have already been annotated. Keywords: BLARK for Persian, PoS tagged corpus, Persian treebank
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/338_Paper.pdf
%P 2245-2252
Markdown (Informal)
[A Basic Language Resource Kit for Persian](http://www.lrec-conf.org/proceedings/lrec2012/pdf/338_Paper.pdf) (Seraji et al., LREC 2012)
ACL
- Mojgan Seraji, Beáta Megyesi, and Joakim Nivre. 2012. A Basic Language Resource Kit for Persian. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2245–2252, Istanbul, Turkey. European Language Resources Association (ELRA).