@inproceedings{heja-takacs-2012-automatically-generated,
title = "Automatically Generated Online Dictionaries",
author = "H{\'e}ja, Enik{\H{o}} and
Tak{\'a}cs, D{\'a}vid",
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/606_Paper.pdf",
pages = "2487--2493",
abstract = "The aim of our software presentation is to demonstrate that corpus-driven bilingual dictionaries generated fully by automatic means are suitable for human use. Need for such dictionaries shows up specifically in the case of lesser used languages where due to the low demand it does not pay off for publishers to invest into the production of dictionaries. Previous experiments have proven that bilingual lexicons can be created by applying word alignment on parallel corpora. Such an approach, especially the corpus-driven nature of it, yields several advantages over more traditional approaches. Most importantly, automatically attained translation probabilities are able to guarantee that the most frequently used translations come first within an entry. However, the proposed technique have to face some difficulties, as well. In particular, the scarce availability of parallel texts for medium density languages imposes limitations on the size of the resulting dictionary. Our objective is to design and implement a dictionary building workflow and a query system that is apt to exploit the additional benefits of the method and overcome the disadvantages of it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heja-takacs-2012-automatically-generated">
<titleInfo>
<title>Automatically Generated Online Dictionaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enikő</namePart>
<namePart type="family">Héja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dávid</namePart>
<namePart type="family">Takács</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>The aim of our software presentation is to demonstrate that corpus-driven bilingual dictionaries generated fully by automatic means are suitable for human use. Need for such dictionaries shows up specifically in the case of lesser used languages where due to the low demand it does not pay off for publishers to invest into the production of dictionaries. Previous experiments have proven that bilingual lexicons can be created by applying word alignment on parallel corpora. Such an approach, especially the corpus-driven nature of it, yields several advantages over more traditional approaches. Most importantly, automatically attained translation probabilities are able to guarantee that the most frequently used translations come first within an entry. However, the proposed technique have to face some difficulties, as well. In particular, the scarce availability of parallel texts for medium density languages imposes limitations on the size of the resulting dictionary. Our objective is to design and implement a dictionary building workflow and a query system that is apt to exploit the additional benefits of the method and overcome the disadvantages of it.</abstract>
<identifier type="citekey">heja-takacs-2012-automatically-generated</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/606_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2487</start>
<end>2493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Generated Online Dictionaries
%A Héja, Enikő
%A Takács, Dávid
%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 heja-takacs-2012-automatically-generated
%X The aim of our software presentation is to demonstrate that corpus-driven bilingual dictionaries generated fully by automatic means are suitable for human use. Need for such dictionaries shows up specifically in the case of lesser used languages where due to the low demand it does not pay off for publishers to invest into the production of dictionaries. Previous experiments have proven that bilingual lexicons can be created by applying word alignment on parallel corpora. Such an approach, especially the corpus-driven nature of it, yields several advantages over more traditional approaches. Most importantly, automatically attained translation probabilities are able to guarantee that the most frequently used translations come first within an entry. However, the proposed technique have to face some difficulties, as well. In particular, the scarce availability of parallel texts for medium density languages imposes limitations on the size of the resulting dictionary. Our objective is to design and implement a dictionary building workflow and a query system that is apt to exploit the additional benefits of the method and overcome the disadvantages of it.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/606_Paper.pdf
%P 2487-2493
Markdown (Informal)
[Automatically Generated Online Dictionaries](http://www.lrec-conf.org/proceedings/lrec2012/pdf/606_Paper.pdf) (Héja & Takács, LREC 2012)
ACL
- Enikő Héja and Dávid Takács. 2012. Automatically Generated Online Dictionaries. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2487–2493, Istanbul, Turkey. European Language Resources Association (ELRA).