@inproceedings{scherrer-cartoni-2012-trilingual,
title = "The Trilingual {ALLEGRA} Corpus: Presentation and Possible Use for Lexicon Induction",
author = "Scherrer, Yves and
Cartoni, Bruno",
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/685_Paper.pdf",
pages = "2890--2896",
abstract = "In this paper, we present a trilingual parallel corpus for German, Italian and Romansh, a Swiss minority language spoken in the canton of Grisons. The corpus called ALLEGRA contains press releases automatically gathered from the website of the cantonal administration of Grisons. Texts have been preprocessed and aligned with a current state-of-the-art sentence aligner. The corpus is one of the first of its kind, and can be of great interest, particularly for the creation of natural language processing resources and tools for Romansh. We illustrate the use of such a trilingual resource for automatic induction of bilingual lexicons, which is a real challenge for under-represented languages. We induce a bilingual lexicon for German-Romansh by phrase alignment and evaluate the resulting entries with the help of a reference lexicon. We then show that the use of the third language of the corpus ― Italian ― as a pivot language can improve the precision of the induced lexicon, without loss in terms of quality of the extracted pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherrer-cartoni-2012-trilingual">
<titleInfo>
<title>The Trilingual ALLEGRA Corpus: Presentation and Possible Use for Lexicon Induction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Cartoni</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 a trilingual parallel corpus for German, Italian and Romansh, a Swiss minority language spoken in the canton of Grisons. The corpus called ALLEGRA contains press releases automatically gathered from the website of the cantonal administration of Grisons. Texts have been preprocessed and aligned with a current state-of-the-art sentence aligner. The corpus is one of the first of its kind, and can be of great interest, particularly for the creation of natural language processing resources and tools for Romansh. We illustrate the use of such a trilingual resource for automatic induction of bilingual lexicons, which is a real challenge for under-represented languages. We induce a bilingual lexicon for German-Romansh by phrase alignment and evaluate the resulting entries with the help of a reference lexicon. We then show that the use of the third language of the corpus ― Italian ― as a pivot language can improve the precision of the induced lexicon, without loss in terms of quality of the extracted pairs.</abstract>
<identifier type="citekey">scherrer-cartoni-2012-trilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/685_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2890</start>
<end>2896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Trilingual ALLEGRA Corpus: Presentation and Possible Use for Lexicon Induction
%A Scherrer, Yves
%A Cartoni, Bruno
%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 scherrer-cartoni-2012-trilingual
%X In this paper, we present a trilingual parallel corpus for German, Italian and Romansh, a Swiss minority language spoken in the canton of Grisons. The corpus called ALLEGRA contains press releases automatically gathered from the website of the cantonal administration of Grisons. Texts have been preprocessed and aligned with a current state-of-the-art sentence aligner. The corpus is one of the first of its kind, and can be of great interest, particularly for the creation of natural language processing resources and tools for Romansh. We illustrate the use of such a trilingual resource for automatic induction of bilingual lexicons, which is a real challenge for under-represented languages. We induce a bilingual lexicon for German-Romansh by phrase alignment and evaluate the resulting entries with the help of a reference lexicon. We then show that the use of the third language of the corpus ― Italian ― as a pivot language can improve the precision of the induced lexicon, without loss in terms of quality of the extracted pairs.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/685_Paper.pdf
%P 2890-2896
Markdown (Informal)
[The Trilingual ALLEGRA Corpus: Presentation and Possible Use for Lexicon Induction](http://www.lrec-conf.org/proceedings/lrec2012/pdf/685_Paper.pdf) (Scherrer & Cartoni, LREC 2012)
ACL