@inproceedings{balvet-etal-2014-talc,
title = "{TALC}-sef A Manually-Revised {POS}-{TA}gged Literary Corpus in {S}erbian, {E}nglish and {F}rench",
author = "Balvet, Antonio and
Stosic, Dejan and
Miletic, Aleksandra",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/755_Paper.pdf",
pages = "4105--4110",
abstract = "In this paper, we present a parallel literary corpus for Serbian, English and French, the TALC-sef corpus. The corpus includes a manually-revised pos-tagged reference Serbian corpus of over 150,000 words. The initial objective was to devise a reference parallel corpus in the three languages, both for literary and linguistic studies. The French and English sub-corpora had been pos-tagged from the onset, using TreeTagger (Schmid, 1994), but the corpus lacked, until now, a tagged version of the Serbian sub-corpus. Here, we present the original parallel literary corpus, then we address issues related to pos-tagging a large collection of Serbian text: from the conception of an appropriate tagset for Serbian, to the choice of an automatic pos-tagger adapted to the task, and then to some quantitative and qualitative results. We then move on to a discussion of perspectives in the near future for further annotations of the whole parallel corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balvet-etal-2014-talc">
<titleInfo>
<title>TALC-sef A Manually-Revised POS-TAgged Literary Corpus in Serbian, English and French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Balvet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dejan</namePart>
<namePart type="family">Stosic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Miletic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a parallel literary corpus for Serbian, English and French, the TALC-sef corpus. The corpus includes a manually-revised pos-tagged reference Serbian corpus of over 150,000 words. The initial objective was to devise a reference parallel corpus in the three languages, both for literary and linguistic studies. The French and English sub-corpora had been pos-tagged from the onset, using TreeTagger (Schmid, 1994), but the corpus lacked, until now, a tagged version of the Serbian sub-corpus. Here, we present the original parallel literary corpus, then we address issues related to pos-tagging a large collection of Serbian text: from the conception of an appropriate tagset for Serbian, to the choice of an automatic pos-tagger adapted to the task, and then to some quantitative and qualitative results. We then move on to a discussion of perspectives in the near future for further annotations of the whole parallel corpus.</abstract>
<identifier type="citekey">balvet-etal-2014-talc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/755_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4105</start>
<end>4110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TALC-sef A Manually-Revised POS-TAgged Literary Corpus in Serbian, English and French
%A Balvet, Antonio
%A Stosic, Dejan
%A Miletic, Aleksandra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F balvet-etal-2014-talc
%X In this paper, we present a parallel literary corpus for Serbian, English and French, the TALC-sef corpus. The corpus includes a manually-revised pos-tagged reference Serbian corpus of over 150,000 words. The initial objective was to devise a reference parallel corpus in the three languages, both for literary and linguistic studies. The French and English sub-corpora had been pos-tagged from the onset, using TreeTagger (Schmid, 1994), but the corpus lacked, until now, a tagged version of the Serbian sub-corpus. Here, we present the original parallel literary corpus, then we address issues related to pos-tagging a large collection of Serbian text: from the conception of an appropriate tagset for Serbian, to the choice of an automatic pos-tagger adapted to the task, and then to some quantitative and qualitative results. We then move on to a discussion of perspectives in the near future for further annotations of the whole parallel corpus.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/755_Paper.pdf
%P 4105-4110
Markdown (Informal)
[TALC-sef A Manually-Revised POS-TAgged Literary Corpus in Serbian, English and French](http://www.lrec-conf.org/proceedings/lrec2014/pdf/755_Paper.pdf) (Balvet et al., LREC 2014)
ACL