@inproceedings{skadina-etal-2012-collecting,
title = "Collecting and Using Comparable Corpora for Statistical Machine Translation",
author = "Skadi{\c{n}}a, Inguna and
Aker, Ahmet and
Mastropavlos, Nikos and
Su, Fangzhong and
Tufis, Dan and
Verlic, Mateja and
Vasi{\c{l}}jevs, Andrejs and
Babych, Bogdan and
Clough, Paul and
Gaizauskas, Robert and
Glaros, Nikos and
Paramita, Monica Lestari and
Pinnis, M{\=a}rcis",
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/925_Paper.pdf",
pages = "438--445",
abstract = "Lack of sufficient parallel data for many languages and domains is currently one of the major obstacles to further advancement of automated translation. The ACCURAT project is addressing this issue by researching methods how to improve machine translation systems by using comparable corpora. In this paper we present tools and techniques developed in the ACCURAT project that allow additional data needed for statistical machine translation to be extracted from comparable corpora. We present methods and tools for acquisition of comparable corpora from the Web and other sources, for evaluation of the comparability of collected corpora, for multi-level alignment of comparable corpora and for extraction of lexical and terminological data for machine translation. Finally, we present initial evaluation results on the utility of collected corpora in domain-adapted machine translation and real-life applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skadina-etal-2012-collecting">
<titleInfo>
<title>Collecting and Using Comparable Corpora for Statistical Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inguna</namePart>
<namePart type="family">Skadiņa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Aker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Mastropavlos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangzhong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateja</namePart>
<namePart type="family">Verlic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrejs</namePart>
<namePart type="family">Vasiļjevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Clough</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Glaros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="given">Lestari</namePart>
<namePart type="family">Paramita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mārcis</namePart>
<namePart type="family">Pinnis</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>Lack of sufficient parallel data for many languages and domains is currently one of the major obstacles to further advancement of automated translation. The ACCURAT project is addressing this issue by researching methods how to improve machine translation systems by using comparable corpora. In this paper we present tools and techniques developed in the ACCURAT project that allow additional data needed for statistical machine translation to be extracted from comparable corpora. We present methods and tools for acquisition of comparable corpora from the Web and other sources, for evaluation of the comparability of collected corpora, for multi-level alignment of comparable corpora and for extraction of lexical and terminological data for machine translation. Finally, we present initial evaluation results on the utility of collected corpora in domain-adapted machine translation and real-life applications.</abstract>
<identifier type="citekey">skadina-etal-2012-collecting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/925_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>438</start>
<end>445</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collecting and Using Comparable Corpora for Statistical Machine Translation
%A Skadiņa, Inguna
%A Aker, Ahmet
%A Mastropavlos, Nikos
%A Su, Fangzhong
%A Tufis, Dan
%A Verlic, Mateja
%A Vasiļjevs, Andrejs
%A Babych, Bogdan
%A Clough, Paul
%A Gaizauskas, Robert
%A Glaros, Nikos
%A Paramita, Monica Lestari
%A Pinnis, Mārcis
%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 skadina-etal-2012-collecting
%X Lack of sufficient parallel data for many languages and domains is currently one of the major obstacles to further advancement of automated translation. The ACCURAT project is addressing this issue by researching methods how to improve machine translation systems by using comparable corpora. In this paper we present tools and techniques developed in the ACCURAT project that allow additional data needed for statistical machine translation to be extracted from comparable corpora. We present methods and tools for acquisition of comparable corpora from the Web and other sources, for evaluation of the comparability of collected corpora, for multi-level alignment of comparable corpora and for extraction of lexical and terminological data for machine translation. Finally, we present initial evaluation results on the utility of collected corpora in domain-adapted machine translation and real-life applications.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/925_Paper.pdf
%P 438-445
Markdown (Informal)
[Collecting and Using Comparable Corpora for Statistical Machine Translation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/925_Paper.pdf) (Skadiņa et al., LREC 2012)
ACL
- Inguna Skadiņa, Ahmet Aker, Nikos Mastropavlos, Fangzhong Su, Dan Tufis, Mateja Verlic, Andrejs Vasiļjevs, Bogdan Babych, Paul Clough, Robert Gaizauskas, Nikos Glaros, Monica Lestari Paramita, and Mārcis Pinnis. 2012. Collecting and Using Comparable Corpora for Statistical Machine Translation. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 438–445, Istanbul, Turkey. European Language Resources Association (ELRA).