@inproceedings{katayama-etal-2024-evaluating,
title = "Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary {J}apanese Texts",
author = "Katayama, Ayuki and
Sakai, Yusuke and
Higashiyama, Shohei and
Ouchi, Hiroki and
Takeuchi, Ayano and
Bando, Ryo and
Hashimoto, Yuta and
Ogiso, Toshinobu and
Watanabe, Taro",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Miyagawa, So and
Alnajjar, Khalid and
Bizzoni, Yuri},
booktitle = "Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities",
month = nov,
year = "2024",
address = "Miami, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4dh-1.33",
pages = "331--338",
abstract = "Automatic extraction of geographic information, including Location Referring Expressions (LREs), can aid humanities research in analyzing large collections of historical texts. In this study, to investigate how accurate pretrained Transformer language models (LMs) can extract LREs from historical texts, we evaluate two representative types of LMs, namely, masked language model and causal language model, using early modern and contemporary Japanese datasets. Our experimental results demonstrated the potential of contemporary LMs for historical texts, but also suggest the need for further model enhancement, such as pretraining on historical texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katayama-etal-2024-evaluating">
<titleInfo>
<title>Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary Japanese Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayuki</namePart>
<namePart type="family">Katayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayano</namePart>
<namePart type="family">Takeuchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Bando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshinobu</namePart>
<namePart type="family">Ogiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic extraction of geographic information, including Location Referring Expressions (LREs), can aid humanities research in analyzing large collections of historical texts. In this study, to investigate how accurate pretrained Transformer language models (LMs) can extract LREs from historical texts, we evaluate two representative types of LMs, namely, masked language model and causal language model, using early modern and contemporary Japanese datasets. Our experimental results demonstrated the potential of contemporary LMs for historical texts, but also suggest the need for further model enhancement, such as pretraining on historical texts.</abstract>
<identifier type="citekey">katayama-etal-2024-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4dh-1.33</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>331</start>
<end>338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary Japanese Texts
%A Katayama, Ayuki
%A Sakai, Yusuke
%A Higashiyama, Shohei
%A Ouchi, Hiroki
%A Takeuchi, Ayano
%A Bando, Ryo
%A Hashimoto, Yuta
%A Ogiso, Toshinobu
%A Watanabe, Taro
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Miyagawa, So
%Y Alnajjar, Khalid
%Y Bizzoni, Yuri
%S Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, USA
%F katayama-etal-2024-evaluating
%X Automatic extraction of geographic information, including Location Referring Expressions (LREs), can aid humanities research in analyzing large collections of historical texts. In this study, to investigate how accurate pretrained Transformer language models (LMs) can extract LREs from historical texts, we evaluate two representative types of LMs, namely, masked language model and causal language model, using early modern and contemporary Japanese datasets. Our experimental results demonstrated the potential of contemporary LMs for historical texts, but also suggest the need for further model enhancement, such as pretraining on historical texts.
%U https://aclanthology.org/2024.nlp4dh-1.33
%P 331-338
Markdown (Informal)
[Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary Japanese Texts](https://aclanthology.org/2024.nlp4dh-1.33) (Katayama et al., NLP4DH 2024)
ACL
- Ayuki Katayama, Yusuke Sakai, Shohei Higashiyama, Hiroki Ouchi, Ayano Takeuchi, Ryo Bando, Yuta Hashimoto, Toshinobu Ogiso, and Taro Watanabe. 2024. Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary Japanese Texts. In Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities, pages 331–338, Miami, USA. Association for Computational Linguistics.