@inproceedings{volk-etal-2014-innovations,
title = "Innovations in Parallel Corpus Search Tools",
author = {Volk, Martin and
Gra{\"e}n, Johannes and
Callegaro, Elena},
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/504_Paper.pdf",
pages = "3172--3178",
abstract = "Recent years have seen an increased interest in and availability of parallel corpora. Large corpora from international organizations (e.g. European Union, United Nations, European Patent Office), or from multilingual Internet sites (e.g. OpenSubtitles) are now easily available and are used for statistical machine translation but also for online search by different user groups. This paper gives an overview of different usages and different types of search systems. In the past, parallel corpus search systems were based on sentence-aligned corpora. We argue that automatic word alignment allows for major innovations in searching parallel corpora. Some online query systems already employ word alignment for sorting translation variants, but none supports the full query functionality that has been developed for parallel treebanks. We propose to develop such a system for efficiently searching large parallel corpora with a powerful query language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volk-etal-2014-innovations">
<titleInfo>
<title>Innovations in Parallel Corpus Search Tools</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Graën</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Callegaro</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>Recent years have seen an increased interest in and availability of parallel corpora. Large corpora from international organizations (e.g. European Union, United Nations, European Patent Office), or from multilingual Internet sites (e.g. OpenSubtitles) are now easily available and are used for statistical machine translation but also for online search by different user groups. This paper gives an overview of different usages and different types of search systems. In the past, parallel corpus search systems were based on sentence-aligned corpora. We argue that automatic word alignment allows for major innovations in searching parallel corpora. Some online query systems already employ word alignment for sorting translation variants, but none supports the full query functionality that has been developed for parallel treebanks. We propose to develop such a system for efficiently searching large parallel corpora with a powerful query language.</abstract>
<identifier type="citekey">volk-etal-2014-innovations</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/504_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3172</start>
<end>3178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Innovations in Parallel Corpus Search Tools
%A Volk, Martin
%A Graën, Johannes
%A Callegaro, Elena
%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 volk-etal-2014-innovations
%X Recent years have seen an increased interest in and availability of parallel corpora. Large corpora from international organizations (e.g. European Union, United Nations, European Patent Office), or from multilingual Internet sites (e.g. OpenSubtitles) are now easily available and are used for statistical machine translation but also for online search by different user groups. This paper gives an overview of different usages and different types of search systems. In the past, parallel corpus search systems were based on sentence-aligned corpora. We argue that automatic word alignment allows for major innovations in searching parallel corpora. Some online query systems already employ word alignment for sorting translation variants, but none supports the full query functionality that has been developed for parallel treebanks. We propose to develop such a system for efficiently searching large parallel corpora with a powerful query language.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/504_Paper.pdf
%P 3172-3178
Markdown (Informal)
[Innovations in Parallel Corpus Search Tools](http://www.lrec-conf.org/proceedings/lrec2014/pdf/504_Paper.pdf) (Volk et al., LREC 2014)
ACL
- Martin Volk, Johannes Graën, and Elena Callegaro. 2014. Innovations in Parallel Corpus Search Tools. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3172–3178, Reykjavik, Iceland. European Language Resources Association (ELRA).