@inproceedings{doyle-mccrae-2025-development,
title = "Development of {O}ld {I}rish Lexical Resources, and Two {U}niversal {D}ependencies Treebanks for Diplomatically Edited {O}ld {I}rish Text",
author = "Doyle, Adrian and
McCrae, John P.",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.34/",
doi = "10.18653/v1/2025.nlp4dh-1.34",
pages = "393--402",
ISBN = "979-8-89176-234-3",
abstract = "The quantity and variety of Old Irish text which survives in contemporary manuscripts, those dating from the Old Irish period, is quite small by comparison to what is available for Modern Irish, not to mention better-resourced modern languages. As no native speakers have existed for more than a millennium, no more text will ever be created by native speakers. For these reasons, text surviving in contemporary sources is particularly valuable. Ideally, all such text would be annotated using a single, common standard to ensure compatibility. At present, discrete Old Irish text repositories make use of incompatible annotation styles, few of which are utilised by text resources for other languages. This limits the potential for using text from more than any one resource simultaneously in NLP applications, or as a basis for creating further resources. This paper describes the production of the first Old Irish text resources to be designed specifically to ensure lexical compatibility and interoperability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doyle-mccrae-2025-development">
<titleInfo>
<title>Development of Old Irish Lexical Resources, and Two Universal Dependencies Treebanks for Diplomatically Edited Old Irish Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Doyle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>The quantity and variety of Old Irish text which survives in contemporary manuscripts, those dating from the Old Irish period, is quite small by comparison to what is available for Modern Irish, not to mention better-resourced modern languages. As no native speakers have existed for more than a millennium, no more text will ever be created by native speakers. For these reasons, text surviving in contemporary sources is particularly valuable. Ideally, all such text would be annotated using a single, common standard to ensure compatibility. At present, discrete Old Irish text repositories make use of incompatible annotation styles, few of which are utilised by text resources for other languages. This limits the potential for using text from more than any one resource simultaneously in NLP applications, or as a basis for creating further resources. This paper describes the production of the first Old Irish text resources to be designed specifically to ensure lexical compatibility and interoperability.</abstract>
<identifier type="citekey">doyle-mccrae-2025-development</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.34</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.34/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>393</start>
<end>402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of Old Irish Lexical Resources, and Two Universal Dependencies Treebanks for Diplomatically Edited Old Irish Text
%A Doyle, Adrian
%A McCrae, John P.
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F doyle-mccrae-2025-development
%X The quantity and variety of Old Irish text which survives in contemporary manuscripts, those dating from the Old Irish period, is quite small by comparison to what is available for Modern Irish, not to mention better-resourced modern languages. As no native speakers have existed for more than a millennium, no more text will ever be created by native speakers. For these reasons, text surviving in contemporary sources is particularly valuable. Ideally, all such text would be annotated using a single, common standard to ensure compatibility. At present, discrete Old Irish text repositories make use of incompatible annotation styles, few of which are utilised by text resources for other languages. This limits the potential for using text from more than any one resource simultaneously in NLP applications, or as a basis for creating further resources. This paper describes the production of the first Old Irish text resources to be designed specifically to ensure lexical compatibility and interoperability.
%R 10.18653/v1/2025.nlp4dh-1.34
%U https://aclanthology.org/2025.nlp4dh-1.34/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.34
%P 393-402
Markdown (Informal)
[Development of Old Irish Lexical Resources, and Two Universal Dependencies Treebanks for Diplomatically Edited Old Irish Text](https://aclanthology.org/2025.nlp4dh-1.34/) (Doyle & McCrae, NLP4DH 2025)
ACL