@inproceedings{al-laith-etal-2024-development-evaluation,
title = "Development and Evaluation of Pre-trained Language Models for Historical {D}anish and {N}orwegian Literary Texts",
author = "Al-Laith, Ali and
Conroy, Alexander and
Bjerring-Hansen, Jens and
Hershcovich, Daniel",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.431",
pages = "4811--4819",
abstract = "We develop and evaluate the first pre-trained language models specifically tailored for historical Danish and Norwegian texts. Three models are trained on a corpus of 19th-century Danish and Norwegian literature: two directly on the corpus with no prior pre-training, and one with continued pre-training. To evaluate the models, we utilize an existing sentiment classification dataset, and additionally introduce a new annotated word sense disambiguation dataset focusing on the concept of fate. Our assessment reveals that the model employing continued pre-training outperforms the others in two downstream NLP tasks on historical texts. Specifically, we observe substantial improvement in sentiment classification and word sense disambiguation compared to models trained on contemporary texts. These results highlight the effectiveness of continued pre-training for enhancing performance across various NLP tasks in historical text analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-laith-etal-2024-development-evaluation">
<titleInfo>
<title>Development and Evaluation of Pre-trained Language Models for Historical Danish and Norwegian Literary Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Laith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Conroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Bjerring-Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We develop and evaluate the first pre-trained language models specifically tailored for historical Danish and Norwegian texts. Three models are trained on a corpus of 19th-century Danish and Norwegian literature: two directly on the corpus with no prior pre-training, and one with continued pre-training. To evaluate the models, we utilize an existing sentiment classification dataset, and additionally introduce a new annotated word sense disambiguation dataset focusing on the concept of fate. Our assessment reveals that the model employing continued pre-training outperforms the others in two downstream NLP tasks on historical texts. Specifically, we observe substantial improvement in sentiment classification and word sense disambiguation compared to models trained on contemporary texts. These results highlight the effectiveness of continued pre-training for enhancing performance across various NLP tasks in historical text analysis.</abstract>
<identifier type="citekey">al-laith-etal-2024-development-evaluation</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.431</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4811</start>
<end>4819</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development and Evaluation of Pre-trained Language Models for Historical Danish and Norwegian Literary Texts
%A Al-Laith, Ali
%A Conroy, Alexander
%A Bjerring-Hansen, Jens
%A Hershcovich, Daniel
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F al-laith-etal-2024-development-evaluation
%X We develop and evaluate the first pre-trained language models specifically tailored for historical Danish and Norwegian texts. Three models are trained on a corpus of 19th-century Danish and Norwegian literature: two directly on the corpus with no prior pre-training, and one with continued pre-training. To evaluate the models, we utilize an existing sentiment classification dataset, and additionally introduce a new annotated word sense disambiguation dataset focusing on the concept of fate. Our assessment reveals that the model employing continued pre-training outperforms the others in two downstream NLP tasks on historical texts. Specifically, we observe substantial improvement in sentiment classification and word sense disambiguation compared to models trained on contemporary texts. These results highlight the effectiveness of continued pre-training for enhancing performance across various NLP tasks in historical text analysis.
%U https://aclanthology.org/2024.lrec-main.431
%P 4811-4819
Markdown (Informal)
[Development and Evaluation of Pre-trained Language Models for Historical Danish and Norwegian Literary Texts](https://aclanthology.org/2024.lrec-main.431) (Al-Laith et al., LREC-COLING 2024)
ACL