@inproceedings{erjavec-2012-goo300k,
title = "The goo300k corpus of historical {S}lovene",
author = "Erjavec, Toma{\v{z}}",
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/445_Paper.pdf",
pages = "2257--2260",
abstract = "The paper presents a gold-standard reference corpus of historical Slovene containing 1,000 sampled pages from over 80 texts, which were, for the most part, written between 1750-1900. Each page of the transcription has an associated facsimile and the words in the texts have been manually annotated with their modern-day equivalent, lemma and part-of-speech. The paper presents the structure of the text collection, the sampling procedure, annotation process and encoding of the corpus. The corpus is meant to facilitate HLT research and enable corpus based diachronic studies for historical Slovene. The corpus is encoded according to the Text Encoding Initiative Guidelines (TEI P5), is available via a concordancer and for download from \url{http://nl.ijs.si/imp/} under the Creative Commons Attribution licence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erjavec-2012-goo300k">
<titleInfo>
<title>The goo300k corpus of historical 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>
<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>The paper presents a gold-standard reference corpus of historical Slovene containing 1,000 sampled pages from over 80 texts, which were, for the most part, written between 1750-1900. Each page of the transcription has an associated facsimile and the words in the texts have been manually annotated with their modern-day equivalent, lemma and part-of-speech. The paper presents the structure of the text collection, the sampling procedure, annotation process and encoding of the corpus. The corpus is meant to facilitate HLT research and enable corpus based diachronic studies for historical Slovene. The corpus is encoded according to the Text Encoding Initiative Guidelines (TEI P5), is available via a concordancer and for download from http://nl.ijs.si/imp/ under the Creative Commons Attribution licence.</abstract>
<identifier type="citekey">erjavec-2012-goo300k</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/445_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2257</start>
<end>2260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The goo300k corpus of historical Slovene
%A Erjavec, Tomaž
%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 erjavec-2012-goo300k
%X The paper presents a gold-standard reference corpus of historical Slovene containing 1,000 sampled pages from over 80 texts, which were, for the most part, written between 1750-1900. Each page of the transcription has an associated facsimile and the words in the texts have been manually annotated with their modern-day equivalent, lemma and part-of-speech. The paper presents the structure of the text collection, the sampling procedure, annotation process and encoding of the corpus. The corpus is meant to facilitate HLT research and enable corpus based diachronic studies for historical Slovene. The corpus is encoded according to the Text Encoding Initiative Guidelines (TEI P5), is available via a concordancer and for download from http://nl.ijs.si/imp/ under the Creative Commons Attribution licence.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/445_Paper.pdf
%P 2257-2260
Markdown (Informal)
[The goo300k corpus of historical Slovene](http://www.lrec-conf.org/proceedings/lrec2012/pdf/445_Paper.pdf) (Erjavec, LREC 2012)
ACL
- Tomaž Erjavec. 2012. The goo300k corpus of historical Slovene. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2257–2260, Istanbul, Turkey. European Language Resources Association (ELRA).