@inproceedings{harju-van-der-goot-2025-age,
title = "How to age {BERT} Well: Continuous Training for Historical Language Adaptation",
author = "Harju, Anika and
van der Goot, Rob",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.21/",
pages = "258--267",
abstract = "As the application of computational tools increases to digitalize historical archives, automatic annotation challenges persist due to distinct linguistic and morphological features of historical languages like Old English (OE). Existing tools struggle with the historical language varieties due to insufficient training. Previous research has focused on adapting pre-trained language models to new languages or domains but has rarely explored the modeling of language variety across time. Hence, we investigate the effectiveness of continuous language model training for adapting language models to OE on domain-specific data. We compare the continuous training of an English model (EN) and a multilingual model (ML), and use POS tagging for downstream evaluation. Results show that continuous pre-training substantially improves performance. We retrain a modern English (EN) model and a Multi-lingual (ML) BERT model for OE. We confirmed the effectiveness of continuous pre-training for language adaptation and downstream evaluation utilizing part-of-speech (POS) tagging, advancing the potential to understand the unique grammatical structures of historical OE archives. More concretely, EN BERT initially outperformed ML BERT with an accuracy of 83{\%} during the language modeling phase. However, on the POS tagging task, ML BERT surpassed EN BERT, achieving an accuracy of 94{\%}, which suggests effective performance to the historical language varieties."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="harju-van-der-goot-2025-age">
<titleInfo>
<title>How to age BERT Well: Continuous Training for Historical Language Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anika</namePart>
<namePart type="family">Harju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</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 First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the application of computational tools increases to digitalize historical archives, automatic annotation challenges persist due to distinct linguistic and morphological features of historical languages like Old English (OE). Existing tools struggle with the historical language varieties due to insufficient training. Previous research has focused on adapting pre-trained language models to new languages or domains but has rarely explored the modeling of language variety across time. Hence, we investigate the effectiveness of continuous language model training for adapting language models to OE on domain-specific data. We compare the continuous training of an English model (EN) and a multilingual model (ML), and use POS tagging for downstream evaluation. Results show that continuous pre-training substantially improves performance. We retrain a modern English (EN) model and a Multi-lingual (ML) BERT model for OE. We confirmed the effectiveness of continuous pre-training for language adaptation and downstream evaluation utilizing part-of-speech (POS) tagging, advancing the potential to understand the unique grammatical structures of historical OE archives. More concretely, EN BERT initially outperformed ML BERT with an accuracy of 83% during the language modeling phase. However, on the POS tagging task, ML BERT surpassed EN BERT, achieving an accuracy of 94%, which suggests effective performance to the historical language varieties.</abstract>
<identifier type="citekey">harju-van-der-goot-2025-age</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.21/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>258</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to age BERT Well: Continuous Training for Historical Language Adaptation
%A Harju, Anika
%A van der Goot, Rob
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F harju-van-der-goot-2025-age
%X As the application of computational tools increases to digitalize historical archives, automatic annotation challenges persist due to distinct linguistic and morphological features of historical languages like Old English (OE). Existing tools struggle with the historical language varieties due to insufficient training. Previous research has focused on adapting pre-trained language models to new languages or domains but has rarely explored the modeling of language variety across time. Hence, we investigate the effectiveness of continuous language model training for adapting language models to OE on domain-specific data. We compare the continuous training of an English model (EN) and a multilingual model (ML), and use POS tagging for downstream evaluation. Results show that continuous pre-training substantially improves performance. We retrain a modern English (EN) model and a Multi-lingual (ML) BERT model for OE. We confirmed the effectiveness of continuous pre-training for language adaptation and downstream evaluation utilizing part-of-speech (POS) tagging, advancing the potential to understand the unique grammatical structures of historical OE archives. More concretely, EN BERT initially outperformed ML BERT with an accuracy of 83% during the language modeling phase. However, on the POS tagging task, ML BERT surpassed EN BERT, achieving an accuracy of 94%, which suggests effective performance to the historical language varieties.
%U https://aclanthology.org/2025.loreslm-1.21/
%P 258-267
Markdown (Informal)
[How to age BERT Well: Continuous Training for Historical Language Adaptation](https://aclanthology.org/2025.loreslm-1.21/) (Harju & van der Goot, LoResLM 2025)
ACL