@inproceedings{stoliarov-etal-2026-conversion,
title = "Conversion of the Clark Hall Dictionary of {O}ld {E}nglish to {TEI} with {RDF}: An End-to-end Pipeline for Lexicographic Resource Retrodigitization",
author = "Stoliarov, Sergei and
Ionov, Maxim and
Khan, Fahad and
Buzzoni, Marina and
Frontini, Francesca",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.561/",
doi = "10.63317/3b2x67e8vd8g",
pages = "7046--7055",
abstract = "In this submission we introduce a workflow/pipeline for creating TEI editions of legacy dictionaries using a parser based on a context-free grammar (CFG). We do this by describing a project which we are currently carrying out and which aims to create a digital edition of an Old English dictionary, Clark-Hall{'}s ``A Concise Anglo-Saxon Dictionary'' using this approach. We begin the article by motivating our CFG-based approach, discussing its advantages and disadvantages, and comparing to it other approaches. We argue that this approach is suitable to certain kinds of dictionaries, such as Clark Hall{'}s. We then describe the microstructure of the dictionary itself with a view both to justifying the kinds of rules which we subsequently describe and to outlining the kinds of resources to which we believe our approach is best suited. We then describe the CFG parser itself and give an account of our experiments in parsing the dictionary. Finally, we outline the enrichment of the parsed dictionary with RDFa and the benefits it has for the published data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stoliarov-etal-2026-conversion">
<titleInfo>
<title>Conversion of the Clark Hall Dictionary of Old English to TEI with RDF: An End-to-end Pipeline for Lexicographic Resource Retrodigitization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergei</namePart>
<namePart type="family">Stoliarov</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">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Buzzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Frontini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this submission we introduce a workflow/pipeline for creating TEI editions of legacy dictionaries using a parser based on a context-free grammar (CFG). We do this by describing a project which we are currently carrying out and which aims to create a digital edition of an Old English dictionary, Clark-Hall’s “A Concise Anglo-Saxon Dictionary” using this approach. We begin the article by motivating our CFG-based approach, discussing its advantages and disadvantages, and comparing to it other approaches. We argue that this approach is suitable to certain kinds of dictionaries, such as Clark Hall’s. We then describe the microstructure of the dictionary itself with a view both to justifying the kinds of rules which we subsequently describe and to outlining the kinds of resources to which we believe our approach is best suited. We then describe the CFG parser itself and give an account of our experiments in parsing the dictionary. Finally, we outline the enrichment of the parsed dictionary with RDFa and the benefits it has for the published data.</abstract>
<identifier type="citekey">stoliarov-etal-2026-conversion</identifier>
<identifier type="doi">10.63317/3b2x67e8vd8g</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.561/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7046</start>
<end>7055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conversion of the Clark Hall Dictionary of Old English to TEI with RDF: An End-to-end Pipeline for Lexicographic Resource Retrodigitization
%A Stoliarov, Sergei
%A Ionov, Maxim
%A Khan, Fahad
%A Buzzoni, Marina
%A Frontini, Francesca
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F stoliarov-etal-2026-conversion
%X In this submission we introduce a workflow/pipeline for creating TEI editions of legacy dictionaries using a parser based on a context-free grammar (CFG). We do this by describing a project which we are currently carrying out and which aims to create a digital edition of an Old English dictionary, Clark-Hall’s “A Concise Anglo-Saxon Dictionary” using this approach. We begin the article by motivating our CFG-based approach, discussing its advantages and disadvantages, and comparing to it other approaches. We argue that this approach is suitable to certain kinds of dictionaries, such as Clark Hall’s. We then describe the microstructure of the dictionary itself with a view both to justifying the kinds of rules which we subsequently describe and to outlining the kinds of resources to which we believe our approach is best suited. We then describe the CFG parser itself and give an account of our experiments in parsing the dictionary. Finally, we outline the enrichment of the parsed dictionary with RDFa and the benefits it has for the published data.
%R 10.63317/3b2x67e8vd8g
%U https://aclanthology.org/2026.lrec-1.561/
%U https://doi.org/10.63317/3b2x67e8vd8g
%P 7046-7055
Markdown (Informal)
[Conversion of the Clark Hall Dictionary of Old English to TEI with RDF: An End-to-end Pipeline for Lexicographic Resource Retrodigitization](https://aclanthology.org/2026.lrec-1.561/) (Stoliarov et al., LREC 2026)
ACL