@inproceedings{hazem-morin-2012-adaptive,
title = "Adaptive Dictionary for Bilingual Lexicon Extraction from Comparable Corpora",
author = "Hazem, Amir and
Morin, Emmanuel",
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/784_Paper.pdf",
pages = "288--292",
abstract = "One of the main resources used for the task of bilingual lexicon extraction from comparable corpora is : the bilingual dictionary, which is considered as a bridge between two languages. However, no particular attention has been given to this lexicon, except its coverage, and the fact that it can be issued from the general language, the specialised one, or a mix of both. In this paper, we want to highlight the idea that a better consideration of the bilingual dictionary by studying its entries and filtering the non-useful ones, leads to a better lexicon extraction and thus, reach a higher precision. The experiments are conducted on a medical domain corpora. The French-English specialised corpus 'breast cancer' of 1 million words. We show that the empirical results obtained with our filtering process improve the standard approach traditionally dedicated to this task and are promising for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazem-morin-2012-adaptive">
<titleInfo>
<title>Adaptive Dictionary for Bilingual Lexicon Extraction from Comparable Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hazem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</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>One of the main resources used for the task of bilingual lexicon extraction from comparable corpora is : the bilingual dictionary, which is considered as a bridge between two languages. However, no particular attention has been given to this lexicon, except its coverage, and the fact that it can be issued from the general language, the specialised one, or a mix of both. In this paper, we want to highlight the idea that a better consideration of the bilingual dictionary by studying its entries and filtering the non-useful ones, leads to a better lexicon extraction and thus, reach a higher precision. The experiments are conducted on a medical domain corpora. The French-English specialised corpus ’breast cancer’ of 1 million words. We show that the empirical results obtained with our filtering process improve the standard approach traditionally dedicated to this task and are promising for future work.</abstract>
<identifier type="citekey">hazem-morin-2012-adaptive</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/784_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>288</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Dictionary for Bilingual Lexicon Extraction from Comparable Corpora
%A Hazem, Amir
%A Morin, Emmanuel
%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 hazem-morin-2012-adaptive
%X One of the main resources used for the task of bilingual lexicon extraction from comparable corpora is : the bilingual dictionary, which is considered as a bridge between two languages. However, no particular attention has been given to this lexicon, except its coverage, and the fact that it can be issued from the general language, the specialised one, or a mix of both. In this paper, we want to highlight the idea that a better consideration of the bilingual dictionary by studying its entries and filtering the non-useful ones, leads to a better lexicon extraction and thus, reach a higher precision. The experiments are conducted on a medical domain corpora. The French-English specialised corpus ’breast cancer’ of 1 million words. We show that the empirical results obtained with our filtering process improve the standard approach traditionally dedicated to this task and are promising for future work.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/784_Paper.pdf
%P 288-292
Markdown (Informal)
[Adaptive Dictionary for Bilingual Lexicon Extraction from Comparable Corpora](http://www.lrec-conf.org/proceedings/lrec2012/pdf/784_Paper.pdf) (Hazem & Morin, LREC 2012)
ACL