@inproceedings{khan-etal-2024-modelling-corpus,
title = "On Modelling Corpus Citations in Computational Lexical Resources",
author = "Khan, Fahad and
Ionov, Maxim and
Chiarcos, Christian and
Romary, Laurent and
S{\'e}rasset, Gilles and
Kabashi, Besim",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1084",
pages = "12385--12394",
abstract = "In this article we look at how two different standards for lexical resources, TEI and OntoLex, deal with corpus citations in lexicons. We will focus on how corpus citations in retrodigitised dictionaries can be modelled using each of the two standards since this provides us with a suitably challenging use case. After looking at the structure of an example entry from a legacy dictionary, we examine the two approaches offered by the two different standards by outlining an encoding for the example entry using both of them (note that this article features the first extended discussion of how the Frequency Attestation and Corpus (FrAC) module of OntoLex deals with citations). After comparing the two approaches and looking at the advantages and disadvantages of both, we argue for a combination of both. In the last part of the article we discuss different ways of doing this, giving our preference for a strategy which makes use of RDFa.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khan-etal-2024-modelling-corpus">
<titleInfo>
<title>On Modelling Corpus Citations in Computational Lexical Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Chiarcos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Romary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Besim</namePart>
<namePart type="family">Kabashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this article we look at how two different standards for lexical resources, TEI and OntoLex, deal with corpus citations in lexicons. We will focus on how corpus citations in retrodigitised dictionaries can be modelled using each of the two standards since this provides us with a suitably challenging use case. After looking at the structure of an example entry from a legacy dictionary, we examine the two approaches offered by the two different standards by outlining an encoding for the example entry using both of them (note that this article features the first extended discussion of how the Frequency Attestation and Corpus (FrAC) module of OntoLex deals with citations). After comparing the two approaches and looking at the advantages and disadvantages of both, we argue for a combination of both. In the last part of the article we discuss different ways of doing this, giving our preference for a strategy which makes use of RDFa.</abstract>
<identifier type="citekey">khan-etal-2024-modelling-corpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1084</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12385</start>
<end>12394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Modelling Corpus Citations in Computational Lexical Resources
%A Khan, Fahad
%A Ionov, Maxim
%A Chiarcos, Christian
%A Romary, Laurent
%A Sérasset, Gilles
%A Kabashi, Besim
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F khan-etal-2024-modelling-corpus
%X In this article we look at how two different standards for lexical resources, TEI and OntoLex, deal with corpus citations in lexicons. We will focus on how corpus citations in retrodigitised dictionaries can be modelled using each of the two standards since this provides us with a suitably challenging use case. After looking at the structure of an example entry from a legacy dictionary, we examine the two approaches offered by the two different standards by outlining an encoding for the example entry using both of them (note that this article features the first extended discussion of how the Frequency Attestation and Corpus (FrAC) module of OntoLex deals with citations). After comparing the two approaches and looking at the advantages and disadvantages of both, we argue for a combination of both. In the last part of the article we discuss different ways of doing this, giving our preference for a strategy which makes use of RDFa.
%U https://aclanthology.org/2024.lrec-main.1084
%P 12385-12394
Markdown (Informal)
[On Modelling Corpus Citations in Computational Lexical Resources](https://aclanthology.org/2024.lrec-main.1084) (Khan et al., LREC-COLING 2024)
ACL
- Fahad Khan, Maxim Ionov, Christian Chiarcos, Laurent Romary, Gilles Sérasset, and Besim Kabashi. 2024. On Modelling Corpus Citations in Computational Lexical Resources. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12385–12394, Torino, Italia. ELRA and ICCL.