@inproceedings{gow-smith-etal-2022-use,
title = "Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore",
author = "Gow-Smith, Edward and
McConville, Mark and
Gillies, William and
Scott, Jade and
{\'O} Maolalaigh, Roibeard",
editor = "Fransen, Theodorus and
Lamb, William and
Prys, Delyth",
booktitle = "Proceedings of the 4th Celtic Language Technology Workshop within LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.cltw-1.13/",
pages = "94--98",
abstract = "The Book of the Dean of Lismore (BDL) is a 16th-century Scottish Gaelic manuscript written in a non-standard orthography. In this work, we outline the problem of transliterating the text of the BDL into a standardised orthography, and perform exploratory experiments using Transformer-based models for this task. In particular, we focus on the task of word-level transliteration, and achieve a character-level BLEU score of 54.15 with our best model, a BART architecture pre-trained on the text of Scottish Gaelic Wikipedia and then fine-tuned on around 2,000 word-level parallel examples. Our initial experiments give promising results, but we highlight the shortcomings of our model, and discuss directions for future work."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gow-smith-etal-2022-use">
<titleInfo>
<title>Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Gow-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">McConville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Gillies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roibeard</namePart>
<namePart type="family">Ó Maolalaigh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Celtic Language Technology Workshop within LREC2022</title>
</titleInfo>
<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">William</namePart>
<namePart type="family">Lamb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delyth</namePart>
<namePart type="family">Prys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Book of the Dean of Lismore (BDL) is a 16th-century Scottish Gaelic manuscript written in a non-standard orthography. In this work, we outline the problem of transliterating the text of the BDL into a standardised orthography, and perform exploratory experiments using Transformer-based models for this task. In particular, we focus on the task of word-level transliteration, and achieve a character-level BLEU score of 54.15 with our best model, a BART architecture pre-trained on the text of Scottish Gaelic Wikipedia and then fine-tuned on around 2,000 word-level parallel examples. Our initial experiments give promising results, but we highlight the shortcomings of our model, and discuss directions for future work.</abstract>
<identifier type="citekey">gow-smith-etal-2022-use</identifier>
<location>
<url>https://aclanthology.org/2022.cltw-1.13/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>94</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore
%A Gow-Smith, Edward
%A McConville, Mark
%A Gillies, William
%A Scott, Jade
%A Ó Maolalaigh, Roibeard
%Y Fransen, Theodorus
%Y Lamb, William
%Y Prys, Delyth
%S Proceedings of the 4th Celtic Language Technology Workshop within LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gow-smith-etal-2022-use
%X The Book of the Dean of Lismore (BDL) is a 16th-century Scottish Gaelic manuscript written in a non-standard orthography. In this work, we outline the problem of transliterating the text of the BDL into a standardised orthography, and perform exploratory experiments using Transformer-based models for this task. In particular, we focus on the task of word-level transliteration, and achieve a character-level BLEU score of 54.15 with our best model, a BART architecture pre-trained on the text of Scottish Gaelic Wikipedia and then fine-tuned on around 2,000 word-level parallel examples. Our initial experiments give promising results, but we highlight the shortcomings of our model, and discuss directions for future work.
%U https://aclanthology.org/2022.cltw-1.13/
%P 94-98
Markdown (Informal)
[Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore](https://aclanthology.org/2022.cltw-1.13/) (Gow-Smith et al., CLTW 2022)
ACL