@inproceedings{weijers-bloem-2025-evaluation,
title = "An evaluation of Named Entity Recognition tools for detecting person names in philosophical text",
author = "Weijers, Ruben and
Bloem, Jelke",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.36/",
doi = "10.18653/v1/2025.nlp4dh-1.36",
pages = "418--425",
ISBN = "979-8-89176-234-3",
abstract = "For philosophers, mentions of the names of other philosophers and scientists are an important indicator of relevance and influence. However, they don{'}t always come in neat citations, especially in older works. We evaluate various approaches to named entity recognition for person names in 20th century, English-language philosophical texts. We use part of a digitized corpus of the works of W.V. Quine, manually annotated for person names, to compare the performance of several systems: the rule-based edhiphy, spaCy{'}s CNN-based system, FLAIR{'}s BiLSTM-based system, and SpanBERT, ERNIE-v2 and ModernBERT{'}s transformer-based approaches. We also experiment with enhancing the smaller models with domain-specific embedding vectors. We find that both spaCy and FLAIR outperform transformer-based models, perhaps due to the small dataset sizes involved."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weijers-bloem-2025-evaluation">
<titleInfo>
<title>An evaluation of Named Entity Recognition tools for detecting person names in philosophical text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Weijers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th 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">Yuri</namePart>
<namePart type="family">Bizzoni</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>For philosophers, mentions of the names of other philosophers and scientists are an important indicator of relevance and influence. However, they don’t always come in neat citations, especially in older works. We evaluate various approaches to named entity recognition for person names in 20th century, English-language philosophical texts. We use part of a digitized corpus of the works of W.V. Quine, manually annotated for person names, to compare the performance of several systems: the rule-based edhiphy, spaCy’s CNN-based system, FLAIR’s BiLSTM-based system, and SpanBERT, ERNIE-v2 and ModernBERT’s transformer-based approaches. We also experiment with enhancing the smaller models with domain-specific embedding vectors. We find that both spaCy and FLAIR outperform transformer-based models, perhaps due to the small dataset sizes involved.</abstract>
<identifier type="citekey">weijers-bloem-2025-evaluation</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.36</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.36/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>418</start>
<end>425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An evaluation of Named Entity Recognition tools for detecting person names in philosophical text
%A Weijers, Ruben
%A Bloem, Jelke
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F weijers-bloem-2025-evaluation
%X For philosophers, mentions of the names of other philosophers and scientists are an important indicator of relevance and influence. However, they don’t always come in neat citations, especially in older works. We evaluate various approaches to named entity recognition for person names in 20th century, English-language philosophical texts. We use part of a digitized corpus of the works of W.V. Quine, manually annotated for person names, to compare the performance of several systems: the rule-based edhiphy, spaCy’s CNN-based system, FLAIR’s BiLSTM-based system, and SpanBERT, ERNIE-v2 and ModernBERT’s transformer-based approaches. We also experiment with enhancing the smaller models with domain-specific embedding vectors. We find that both spaCy and FLAIR outperform transformer-based models, perhaps due to the small dataset sizes involved.
%R 10.18653/v1/2025.nlp4dh-1.36
%U https://aclanthology.org/2025.nlp4dh-1.36/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.36
%P 418-425
Markdown (Informal)
[An evaluation of Named Entity Recognition tools for detecting person names in philosophical text](https://aclanthology.org/2025.nlp4dh-1.36/) (Weijers & Bloem, NLP4DH 2025)
ACL