@inproceedings{dereza-etal-2023-temporal,
title = "Temporal Domain Adaptation for Historical {I}rish",
author = "Dereza, Oksana and
Fransen, Theodorus and
Mccrae, John P.",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, J{\"o}rg and
Zampieri, Marcos},
booktitle = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.vardial-1.6",
doi = "10.18653/v1/2023.vardial-1.6",
pages = "55--66",
abstract = "The digitisation of historical texts has provided new horizons for NLP research, but such data also presents a set of challenges, including scarcity and inconsistency. The lack of editorial standard during digitisation exacerbates these difficulties. This study explores the potential for temporal domain adaptation in Early Modern Irish and pre-reform Modern Irish data. We describe two experiments carried out on the book subcorpus of the Historical Irish Corpus, which includes Early Modern Irish and pre-reform Modern Irish texts from 1581 to 1926. We also propose a simple orthographic normalisation method for historical Irish that reduces the type-token ratio by 21.43{\%} on average in our data. The results demonstrate that the use of out-of-domain data significantly improves a language model{'}s performance. Providing a model with additional input from another historical stage of the language improves its quality by 12.49{\%} on average on non-normalised texts and by 27.02{\%} on average on normalised (demutated) texts. Most notably, using only out-of-domain data for both pre-training and training stages allowed for up to 86.81{\%} of the baseline model quality on non-normalised texts and up to 95.68{\%} on normalised texts without any target domain data. Additionally, we investigate the effect of temporal distance between the training and test data. The hypothesis that there is a positive correlation between performance and temporal proximity of training and test data has been validated, which manifests best in normalised data. Expanding this approach even further back, to Middle and Old Irish, and testing it on other languages is a further research direction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dereza-etal-2023-temporal">
<titleInfo>
<title>Temporal Domain Adaptation for Historical Irish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oksana</namePart>
<namePart type="family">Dereza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</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>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The digitisation of historical texts has provided new horizons for NLP research, but such data also presents a set of challenges, including scarcity and inconsistency. The lack of editorial standard during digitisation exacerbates these difficulties. This study explores the potential for temporal domain adaptation in Early Modern Irish and pre-reform Modern Irish data. We describe two experiments carried out on the book subcorpus of the Historical Irish Corpus, which includes Early Modern Irish and pre-reform Modern Irish texts from 1581 to 1926. We also propose a simple orthographic normalisation method for historical Irish that reduces the type-token ratio by 21.43% on average in our data. The results demonstrate that the use of out-of-domain data significantly improves a language model’s performance. Providing a model with additional input from another historical stage of the language improves its quality by 12.49% on average on non-normalised texts and by 27.02% on average on normalised (demutated) texts. Most notably, using only out-of-domain data for both pre-training and training stages allowed for up to 86.81% of the baseline model quality on non-normalised texts and up to 95.68% on normalised texts without any target domain data. Additionally, we investigate the effect of temporal distance between the training and test data. The hypothesis that there is a positive correlation between performance and temporal proximity of training and test data has been validated, which manifests best in normalised data. Expanding this approach even further back, to Middle and Old Irish, and testing it on other languages is a further research direction.</abstract>
<identifier type="citekey">dereza-etal-2023-temporal</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.6</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.6</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>55</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal Domain Adaptation for Historical Irish
%A Dereza, Oksana
%A Fransen, Theodorus
%A Mccrae, John P.
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F dereza-etal-2023-temporal
%X The digitisation of historical texts has provided new horizons for NLP research, but such data also presents a set of challenges, including scarcity and inconsistency. The lack of editorial standard during digitisation exacerbates these difficulties. This study explores the potential for temporal domain adaptation in Early Modern Irish and pre-reform Modern Irish data. We describe two experiments carried out on the book subcorpus of the Historical Irish Corpus, which includes Early Modern Irish and pre-reform Modern Irish texts from 1581 to 1926. We also propose a simple orthographic normalisation method for historical Irish that reduces the type-token ratio by 21.43% on average in our data. The results demonstrate that the use of out-of-domain data significantly improves a language model’s performance. Providing a model with additional input from another historical stage of the language improves its quality by 12.49% on average on non-normalised texts and by 27.02% on average on normalised (demutated) texts. Most notably, using only out-of-domain data for both pre-training and training stages allowed for up to 86.81% of the baseline model quality on non-normalised texts and up to 95.68% on normalised texts without any target domain data. Additionally, we investigate the effect of temporal distance between the training and test data. The hypothesis that there is a positive correlation between performance and temporal proximity of training and test data has been validated, which manifests best in normalised data. Expanding this approach even further back, to Middle and Old Irish, and testing it on other languages is a further research direction.
%R 10.18653/v1/2023.vardial-1.6
%U https://aclanthology.org/2023.vardial-1.6
%U https://doi.org/10.18653/v1/2023.vardial-1.6
%P 55-66
Markdown (Informal)
[Temporal Domain Adaptation for Historical Irish](https://aclanthology.org/2023.vardial-1.6) (Dereza et al., VarDial 2023)
ACL
- Oksana Dereza, Theodorus Fransen, and John P. Mccrae. 2023. Temporal Domain Adaptation for Historical Irish. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 55–66, Dubrovnik, Croatia. Association for Computational Linguistics.