@inproceedings{doyle-mccrae-2025-assessment,
title = "An Assessment of Word Separation Practices in {O}ld {I}rish Text Resources and a Universal Method for Tokenising {O}ld {I}rish Text",
author = "Doyle, Adrian and
McCrae, John P.",
editor = "Davis, Brian and
Fransen, Theodorus and
Dhonnchadha, Elaine Ui and
Walsh, Abigail",
booktitle = "Proceedings of the 5th Celtic Language Technology Workshop",
month = jan,
year = "2025",
address = "Abu Dhabi [Virtual Workshop]",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.cltw-1.1/",
pages = "1--11",
abstract = "The quantity of Old Irish text which survives in contemporary manuscripts is relatively small by comparison to what is available for well-resourced modern languages. Moreover, as it is a historical language, no more text will ever be generated by native speakers of Old Irish. This makes the text which has survived particularly valuable, and ideally, all of it would be annotated using a single, common annotation standard, thereby ensuring compatibility between text resources. At present, Old Irish text repositories separate words or sub-word morphemes in accordance with different methodologies, and each uses a different style of lexical annotation. This makes it difficult to utilise content from more than any one repository in NLP applications. This paper provides an assessment of distinctions between existing annotated corpora, showing that the primary point of divergence is at the token level. For this reason, this paper also describes a new method for tokenising Old Irish text. This method can be applied even to diplomatic editions, and has already been utilised in various text resources."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doyle-mccrae-2025-assessment">
<titleInfo>
<title>An Assessment of Word Separation Practices in Old Irish Text Resources and a Universal Method for Tokenising 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>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Celtic Language Technology Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaine</namePart>
<namePart type="given">Ui</namePart>
<namePart type="family">Dhonnchadha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abigail</namePart>
<namePart type="family">Walsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi [Virtual Workshop]</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The quantity of Old Irish text which survives in contemporary manuscripts is relatively small by comparison to what is available for well-resourced modern languages. Moreover, as it is a historical language, no more text will ever be generated by native speakers of Old Irish. This makes the text which has survived particularly valuable, and ideally, all of it would be annotated using a single, common annotation standard, thereby ensuring compatibility between text resources. At present, Old Irish text repositories separate words or sub-word morphemes in accordance with different methodologies, and each uses a different style of lexical annotation. This makes it difficult to utilise content from more than any one repository in NLP applications. This paper provides an assessment of distinctions between existing annotated corpora, showing that the primary point of divergence is at the token level. For this reason, this paper also describes a new method for tokenising Old Irish text. This method can be applied even to diplomatic editions, and has already been utilised in various text resources.</abstract>
<identifier type="citekey">doyle-mccrae-2025-assessment</identifier>
<location>
<url>https://aclanthology.org/2025.cltw-1.1/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Assessment of Word Separation Practices in Old Irish Text Resources and a Universal Method for Tokenising Old Irish Text
%A Doyle, Adrian
%A McCrae, John P.
%Y Davis, Brian
%Y Fransen, Theodorus
%Y Dhonnchadha, Elaine Ui
%Y Walsh, Abigail
%S Proceedings of the 5th Celtic Language Technology Workshop
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi [Virtual Workshop]
%F doyle-mccrae-2025-assessment
%X The quantity of Old Irish text which survives in contemporary manuscripts is relatively small by comparison to what is available for well-resourced modern languages. Moreover, as it is a historical language, no more text will ever be generated by native speakers of Old Irish. This makes the text which has survived particularly valuable, and ideally, all of it would be annotated using a single, common annotation standard, thereby ensuring compatibility between text resources. At present, Old Irish text repositories separate words or sub-word morphemes in accordance with different methodologies, and each uses a different style of lexical annotation. This makes it difficult to utilise content from more than any one repository in NLP applications. This paper provides an assessment of distinctions between existing annotated corpora, showing that the primary point of divergence is at the token level. For this reason, this paper also describes a new method for tokenising Old Irish text. This method can be applied even to diplomatic editions, and has already been utilised in various text resources.
%U https://aclanthology.org/2025.cltw-1.1/
%P 1-11
Markdown (Informal)
[An Assessment of Word Separation Practices in Old Irish Text Resources and a Universal Method for Tokenising Old Irish Text](https://aclanthology.org/2025.cltw-1.1/) (Doyle & McCrae, CLTW 2025)
ACL