@inproceedings{erjavec-etal-2010-jos,
title = "The {JOS} Linguistically Tagged Corpus of {S}lovene",
author = "Erjavec, Toma{\v{z}} and
Fi{\v{s}}er, Darja and
Krek, Simon and
Ledinek, Nina",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/139_Paper.pdf",
abstract = "The JOS language resources are meant to facilitate developments of HLT and corpus linguistics for the Slovene language and consist of the morphosyntactic specifications, defining the Slovene morphosyntactic features and tagset; two annotated corpora (jos100k and jos1M); and two web services (a concordancer and text annotation tool). The paper introduces these components, and concentrates on jos100k, a 100,000 word sampled balanced monolingual Slovene corpus, manually annotated for three levels of linguistic description. On the morphosyntactic level, each word is annotated with its morphosyntactic description and lemma; on the syntactic level the sentences are annotated with dependency links; on the semantic level, all the occurrences of 100 top nouns in the corpus are annotated with their wordnet synset from the Slovene semantic lexicon sloWNet. The JOS corpora and specifications have a standardised encoding (Text Encoding Initiative Guidelines TEI P5) and are available for research from \url{http://nl.ijs.si/jos/} under the Creative Commons licence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erjavec-etal-2010-jos">
<titleInfo>
<title>The JOS Linguistically Tagged Corpus of Slovene</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Ledinek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The JOS language resources are meant to facilitate developments of HLT and corpus linguistics for the Slovene language and consist of the morphosyntactic specifications, defining the Slovene morphosyntactic features and tagset; two annotated corpora (jos100k and jos1M); and two web services (a concordancer and text annotation tool). The paper introduces these components, and concentrates on jos100k, a 100,000 word sampled balanced monolingual Slovene corpus, manually annotated for three levels of linguistic description. On the morphosyntactic level, each word is annotated with its morphosyntactic description and lemma; on the syntactic level the sentences are annotated with dependency links; on the semantic level, all the occurrences of 100 top nouns in the corpus are annotated with their wordnet synset from the Slovene semantic lexicon sloWNet. The JOS corpora and specifications have a standardised encoding (Text Encoding Initiative Guidelines TEI P5) and are available for research from http://nl.ijs.si/jos/ under the Creative Commons licence.</abstract>
<identifier type="citekey">erjavec-etal-2010-jos</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/139_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The JOS Linguistically Tagged Corpus of Slovene
%A Erjavec, Tomaž
%A Fišer, Darja
%A Krek, Simon
%A Ledinek, Nina
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F erjavec-etal-2010-jos
%X The JOS language resources are meant to facilitate developments of HLT and corpus linguistics for the Slovene language and consist of the morphosyntactic specifications, defining the Slovene morphosyntactic features and tagset; two annotated corpora (jos100k and jos1M); and two web services (a concordancer and text annotation tool). The paper introduces these components, and concentrates on jos100k, a 100,000 word sampled balanced monolingual Slovene corpus, manually annotated for three levels of linguistic description. On the morphosyntactic level, each word is annotated with its morphosyntactic description and lemma; on the syntactic level the sentences are annotated with dependency links; on the semantic level, all the occurrences of 100 top nouns in the corpus are annotated with their wordnet synset from the Slovene semantic lexicon sloWNet. The JOS corpora and specifications have a standardised encoding (Text Encoding Initiative Guidelines TEI P5) and are available for research from http://nl.ijs.si/jos/ under the Creative Commons licence.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/139_Paper.pdf
Markdown (Informal)
[The JOS Linguistically Tagged Corpus of Slovene](http://www.lrec-conf.org/proceedings/lrec2010/pdf/139_Paper.pdf) (Erjavec et al., LREC 2010)
ACL
- Tomaž Erjavec, Darja Fišer, Simon Krek, and Nina Ledinek. 2010. The JOS Linguistically Tagged Corpus of Slovene. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).