@inproceedings{cebovic-tadic-2016-building,
title = "Building the {M}acedonian-{C}roatian Parallel Corpus",
author = "Cebovi{\'c}, Ines and
Tadi{\'c}, Marko",
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/L16-1671",
pages = "4241--4244",
abstract = "In this paper we present the newly created parallel corpus of two under-resourced languages, namely, Macedonian-Croatian Parallel Corpus (mk-hr{\_}pcorp) that has been collected during 2015 at the Faculty of Humanities and Social Sciences, University of Zagreb. The mk-hr{\_}pcorp is a unidirectional (mk→hr) parallel corpus composed of synchronic fictional prose texts received already in digital form with over 500 Kw in each language. The corpus was sentence segmented and provides 39,735 aligned sentences. The alignment was done automatically and then post-corrected manually. The alignments order was shuffled and this enabled the corpus to be available under CC-BY license through META-SHARE. However, this prevents the research in language units over the sentence level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cebovic-tadic-2016-building">
<titleInfo>
<title>Building the Macedonian-Croatian Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ines</namePart>
<namePart type="family">Cebović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Tadić</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>In this paper we present the newly created parallel corpus of two under-resourced languages, namely, Macedonian-Croatian Parallel Corpus (mk-hr_pcorp) that has been collected during 2015 at the Faculty of Humanities and Social Sciences, University of Zagreb. The mk-hr_pcorp is a unidirectional (mk→hr) parallel corpus composed of synchronic fictional prose texts received already in digital form with over 500 Kw in each language. The corpus was sentence segmented and provides 39,735 aligned sentences. The alignment was done automatically and then post-corrected manually. The alignments order was shuffled and this enabled the corpus to be available under CC-BY license through META-SHARE. However, this prevents the research in language units over the sentence level.</abstract>
<identifier type="citekey">cebovic-tadic-2016-building</identifier>
<location>
<url>https://aclanthology.org/L16-1671</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4241</start>
<end>4244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building the Macedonian-Croatian Parallel Corpus
%A Cebović, Ines
%A Tadić, Marko
%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 cebovic-tadic-2016-building
%X In this paper we present the newly created parallel corpus of two under-resourced languages, namely, Macedonian-Croatian Parallel Corpus (mk-hr_pcorp) that has been collected during 2015 at the Faculty of Humanities and Social Sciences, University of Zagreb. The mk-hr_pcorp is a unidirectional (mk→hr) parallel corpus composed of synchronic fictional prose texts received already in digital form with over 500 Kw in each language. The corpus was sentence segmented and provides 39,735 aligned sentences. The alignment was done automatically and then post-corrected manually. The alignments order was shuffled and this enabled the corpus to be available under CC-BY license through META-SHARE. However, this prevents the research in language units over the sentence level.
%U https://aclanthology.org/L16-1671
%P 4241-4244
Markdown (Informal)
[Building the Macedonian-Croatian Parallel Corpus](https://aclanthology.org/L16-1671) (Cebović & Tadić, LREC 2016)
ACL
- Ines Cebović and Marko Tadić. 2016. Building the Macedonian-Croatian Parallel Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4241–4244, Portorož, Slovenia. European Language Resources Association (ELRA).