@inproceedings{fourrier-sagot-2020-methodological,
title = "Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing {E}tym{DB}-2.0",
author = "Fourrier, Cl{\'e}mentine and
Sagot, Beno{\^\i}t",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.392",
pages = "3207--3216",
abstract = "Diachronic lexical information is not only important in the field of historical linguistics, but is also increasingly used in NLP, most recently for machine translation of low resource languages. Therefore, there is a need for fine-grained, large-coverage and accurate etymological lexical resources. In this paper, we propose a set of guidelines to generate such resources, for each step of the life-cycle of an etymological lexicon: creation, update, evaluation, dissemination, and exploitation. To illustrate the guidelines, we introduce EtymDB 2.0, an etymological database automatically generated from the Wiktionary, which contains 1.8 million lexemes, linked by more than 700,000 fine-grained etymological relations, across 2,536 living and dead languages. We also introduce use cases for which EtymDB 2.0 could represent a key resource, such as phylogenetic tree generation, low resource machine translation or medieval languages study.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fourrier-sagot-2020-methodological">
<titleInfo>
<title>Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing EtymDB-2.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Clémentine</namePart>
<namePart type="family">Fourrier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Diachronic lexical information is not only important in the field of historical linguistics, but is also increasingly used in NLP, most recently for machine translation of low resource languages. Therefore, there is a need for fine-grained, large-coverage and accurate etymological lexical resources. In this paper, we propose a set of guidelines to generate such resources, for each step of the life-cycle of an etymological lexicon: creation, update, evaluation, dissemination, and exploitation. To illustrate the guidelines, we introduce EtymDB 2.0, an etymological database automatically generated from the Wiktionary, which contains 1.8 million lexemes, linked by more than 700,000 fine-grained etymological relations, across 2,536 living and dead languages. We also introduce use cases for which EtymDB 2.0 could represent a key resource, such as phylogenetic tree generation, low resource machine translation or medieval languages study.</abstract>
<identifier type="citekey">fourrier-sagot-2020-methodological</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.392</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>3207</start>
<end>3216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing EtymDB-2.0
%A Fourrier, Clémentine
%A Sagot, Benoît
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F fourrier-sagot-2020-methodological
%X Diachronic lexical information is not only important in the field of historical linguistics, but is also increasingly used in NLP, most recently for machine translation of low resource languages. Therefore, there is a need for fine-grained, large-coverage and accurate etymological lexical resources. In this paper, we propose a set of guidelines to generate such resources, for each step of the life-cycle of an etymological lexicon: creation, update, evaluation, dissemination, and exploitation. To illustrate the guidelines, we introduce EtymDB 2.0, an etymological database automatically generated from the Wiktionary, which contains 1.8 million lexemes, linked by more than 700,000 fine-grained etymological relations, across 2,536 living and dead languages. We also introduce use cases for which EtymDB 2.0 could represent a key resource, such as phylogenetic tree generation, low resource machine translation or medieval languages study.
%U https://aclanthology.org/2020.lrec-1.392
%P 3207-3216
Markdown (Informal)
[Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing EtymDB-2.0](https://aclanthology.org/2020.lrec-1.392) (Fourrier & Sagot, LREC 2020)
ACL