@inproceedings{dinu-ciobanu-2014-building,
title = "Building a Dataset of Multilingual Cognates for the {R}omanian Lexicon",
author = "Dinu, Liviu and
Ciobanu, Alina Maria",
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/175_Paper.pdf",
pages = "1038--1043",
abstract = "Identifying cognates is an interesting task with applications in numerous research areas, such as historical and comparative linguistics, language acquisition, cross-lingual information retrieval, readability and machine translation. We propose a dictionary-based approach to identifying cognates based on etymology and etymons. We account for relationships between languages and we extract etymology-related information from electronic dictionaries. We employ the dataset of cognates that we obtain as a gold standard for evaluating to which extent orthographic methods can be used to detect cognate pairs. The question that arises is whether they are able to discriminate between cognates and non-cognates, given the orthographic changes undergone by foreign words when entering new languages. We investigate some orthographic approaches widely used in this research area and some original metrics as well. We run our experiments on the Romanian lexicon, but the method we propose is adaptable to any language, as far as resources are available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinu-ciobanu-2014-building">
<titleInfo>
<title>Building a Dataset of Multilingual Cognates for the Romanian Lexicon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ciobanu</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>Identifying cognates is an interesting task with applications in numerous research areas, such as historical and comparative linguistics, language acquisition, cross-lingual information retrieval, readability and machine translation. We propose a dictionary-based approach to identifying cognates based on etymology and etymons. We account for relationships between languages and we extract etymology-related information from electronic dictionaries. We employ the dataset of cognates that we obtain as a gold standard for evaluating to which extent orthographic methods can be used to detect cognate pairs. The question that arises is whether they are able to discriminate between cognates and non-cognates, given the orthographic changes undergone by foreign words when entering new languages. We investigate some orthographic approaches widely used in this research area and some original metrics as well. We run our experiments on the Romanian lexicon, but the method we propose is adaptable to any language, as far as resources are available.</abstract>
<identifier type="citekey">dinu-ciobanu-2014-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/175_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1038</start>
<end>1043</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Dataset of Multilingual Cognates for the Romanian Lexicon
%A Dinu, Liviu
%A Ciobanu, Alina Maria
%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 dinu-ciobanu-2014-building
%X Identifying cognates is an interesting task with applications in numerous research areas, such as historical and comparative linguistics, language acquisition, cross-lingual information retrieval, readability and machine translation. We propose a dictionary-based approach to identifying cognates based on etymology and etymons. We account for relationships between languages and we extract etymology-related information from electronic dictionaries. We employ the dataset of cognates that we obtain as a gold standard for evaluating to which extent orthographic methods can be used to detect cognate pairs. The question that arises is whether they are able to discriminate between cognates and non-cognates, given the orthographic changes undergone by foreign words when entering new languages. We investigate some orthographic approaches widely used in this research area and some original metrics as well. We run our experiments on the Romanian lexicon, but the method we propose is adaptable to any language, as far as resources are available.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/175_Paper.pdf
%P 1038-1043
Markdown (Informal)
[Building a Dataset of Multilingual Cognates for the Romanian Lexicon](http://www.lrec-conf.org/proceedings/lrec2014/pdf/175_Paper.pdf) (Dinu & Ciobanu, LREC 2014)
ACL