@inproceedings{szabo-etal-2012-hunor,
title = "{H}un{O}r: A {H}ungarian{---}{R}ussian Parallel Corpus",
author = "Szab{\'o}, Martina Katalin and
Vincze, Veronika and
Nagy T., Istv{\'a}n",
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/262_Paper.pdf",
pages = "2453--2458",
abstract = "In this paper, we present HunOr, the first multi-domain Hungarian―Russian parallel corpus. Some of the corpus texts have been manually aligned and split into sentences, besides, named entities also have been annotated while the other parts are automatically aligned at the sentence level and they are POS-tagged as well. The corpus contains texts from the domains literature, official language use and science, however, we would like to add texts from the news domain to the corpus. In the future, we are planning to carry out a syntactic annotation of the HunOr corpus, which will further enhance the usability of the corpus in various NLP fields such as transfer-based machine translation or cross lingual information retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szabo-etal-2012-hunor">
<titleInfo>
<title>HunOr: A Hungarian—Russian Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="given">Katalin</namePart>
<namePart type="family">Szabó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Vincze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">István</namePart>
<namePart type="family">Nagy T.</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>In this paper, we present HunOr, the first multi-domain Hungarian―Russian parallel corpus. Some of the corpus texts have been manually aligned and split into sentences, besides, named entities also have been annotated while the other parts are automatically aligned at the sentence level and they are POS-tagged as well. The corpus contains texts from the domains literature, official language use and science, however, we would like to add texts from the news domain to the corpus. In the future, we are planning to carry out a syntactic annotation of the HunOr corpus, which will further enhance the usability of the corpus in various NLP fields such as transfer-based machine translation or cross lingual information retrieval.</abstract>
<identifier type="citekey">szabo-etal-2012-hunor</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/262_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2453</start>
<end>2458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HunOr: A Hungarian—Russian Parallel Corpus
%A Szabó, Martina Katalin
%A Vincze, Veronika
%A Nagy T., István
%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 szabo-etal-2012-hunor
%X In this paper, we present HunOr, the first multi-domain Hungarian―Russian parallel corpus. Some of the corpus texts have been manually aligned and split into sentences, besides, named entities also have been annotated while the other parts are automatically aligned at the sentence level and they are POS-tagged as well. The corpus contains texts from the domains literature, official language use and science, however, we would like to add texts from the news domain to the corpus. In the future, we are planning to carry out a syntactic annotation of the HunOr corpus, which will further enhance the usability of the corpus in various NLP fields such as transfer-based machine translation or cross lingual information retrieval.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/262_Paper.pdf
%P 2453-2458
Markdown (Informal)
[HunOr: A Hungarian—Russian Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/262_Paper.pdf) (Szabó et al., LREC 2012)
ACL
- Martina Katalin Szabó, Veronika Vincze, and István Nagy T.. 2012. HunOr: A Hungarian—Russian Parallel Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2453–2458, Istanbul, Turkey. European Language Resources Association (ELRA).