@inproceedings{dubey-etal-2014-enrichment,
title = "Enrichment of Bilingual Dictionary through News Stream Data",
author = "Dubey, Ajay and
Gupta, Parth and
Varma, Vasudeva and
Rosso, Paolo",
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/1105_Paper.pdf",
pages = "3761--3765",
abstract = "Bilingual dictionaries are the key component of the cross-lingual similarity estimation methods. Usually such dictionary generation is accomplished by manual or automatic means. Automatic generation approaches include to exploit parallel or comparable data to derive dictionary entries. Such approaches require large amount of bilingual data in order to produce good quality dictionary. Many time the language pair does not have large bilingual comparable corpora and in such cases the best automatic dictionary is upper bounded by the quality and coverage of such corpora. In this work we propose a method which exploits continuous quasi-comparable corpora to derive term level associations for enrichment of such limited dictionary. Though we propose our experiments for English and Hindi, our approach can be easily extendable to other languages. We evaluated dictionary by manually computing the precision. In experiments we show our approach is able to derive interesting term level associations across languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dubey-etal-2014-enrichment">
<titleInfo>
<title>Enrichment of Bilingual Dictionary through News Stream Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ajay</namePart>
<namePart type="family">Dubey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parth</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudeva</namePart>
<namePart type="family">Varma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Rosso</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>Bilingual dictionaries are the key component of the cross-lingual similarity estimation methods. Usually such dictionary generation is accomplished by manual or automatic means. Automatic generation approaches include to exploit parallel or comparable data to derive dictionary entries. Such approaches require large amount of bilingual data in order to produce good quality dictionary. Many time the language pair does not have large bilingual comparable corpora and in such cases the best automatic dictionary is upper bounded by the quality and coverage of such corpora. In this work we propose a method which exploits continuous quasi-comparable corpora to derive term level associations for enrichment of such limited dictionary. Though we propose our experiments for English and Hindi, our approach can be easily extendable to other languages. We evaluated dictionary by manually computing the precision. In experiments we show our approach is able to derive interesting term level associations across languages.</abstract>
<identifier type="citekey">dubey-etal-2014-enrichment</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1105_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3761</start>
<end>3765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enrichment of Bilingual Dictionary through News Stream Data
%A Dubey, Ajay
%A Gupta, Parth
%A Varma, Vasudeva
%A Rosso, Paolo
%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 dubey-etal-2014-enrichment
%X Bilingual dictionaries are the key component of the cross-lingual similarity estimation methods. Usually such dictionary generation is accomplished by manual or automatic means. Automatic generation approaches include to exploit parallel or comparable data to derive dictionary entries. Such approaches require large amount of bilingual data in order to produce good quality dictionary. Many time the language pair does not have large bilingual comparable corpora and in such cases the best automatic dictionary is upper bounded by the quality and coverage of such corpora. In this work we propose a method which exploits continuous quasi-comparable corpora to derive term level associations for enrichment of such limited dictionary. Though we propose our experiments for English and Hindi, our approach can be easily extendable to other languages. We evaluated dictionary by manually computing the precision. In experiments we show our approach is able to derive interesting term level associations across languages.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1105_Paper.pdf
%P 3761-3765
Markdown (Informal)
[Enrichment of Bilingual Dictionary through News Stream Data](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1105_Paper.pdf) (Dubey et al., LREC 2014)
ACL
- Ajay Dubey, Parth Gupta, Vasudeva Varma, and Paolo Rosso. 2014. Enrichment of Bilingual Dictionary through News Stream Data. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3761–3765, Reykjavik, Iceland. European Language Resources Association (ELRA).