@inproceedings{fang-etal-2025-comparative,
title = "A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical {C}hinese Sources, 1900-1950",
author = "Fang, Zhao and
Wu, Liang-Chun and
Kong, Xuening and
Stewart, Spencer Dean",
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-1.1/",
doi = "10.18653/v1/2025.nlp4dh-1.1",
pages = "1--6",
ISBN = "979-8-89176-234-3",
abstract = "This paper compares large language models (LLMs) and traditional natural language processing (NLP) tools for performing word segmentation, part-of-speech (POS) tagging, and named entity recognition (NER) on Chinese texts from 1900 to 1950. Historical Chinese documents pose challenges for text analysis due to their logographic script, the absence of natural word boundaries, and significant linguistic changes. Using a sample dataset from the Shanghai Library Republican Journal corpus, traditional tools such as Jieba and spaCy are compared to LLMs, including GPT-4o, Claude 3.5, and the GLM series. The results show that LLMs outperform traditional methods in all metrics, albeit at considerably higher computational costs, highlighting a trade-off between accuracy and efficiency. Additionally, LLMs better handle genre-specific challenges such as poetry and temporal variations (i.e., pre-1920 versus post-1920 texts), demonstrating that their contextual learning capabilities can advance NLP approaches to historical texts by reducing the need for domain-specific training data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2025-comparative">
<titleInfo>
<title>A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang-Chun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuening</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spencer</namePart>
<namePart type="given">Dean</namePart>
<namePart type="family">Stewart</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>This paper compares large language models (LLMs) and traditional natural language processing (NLP) tools for performing word segmentation, part-of-speech (POS) tagging, and named entity recognition (NER) on Chinese texts from 1900 to 1950. Historical Chinese documents pose challenges for text analysis due to their logographic script, the absence of natural word boundaries, and significant linguistic changes. Using a sample dataset from the Shanghai Library Republican Journal corpus, traditional tools such as Jieba and spaCy are compared to LLMs, including GPT-4o, Claude 3.5, and the GLM series. The results show that LLMs outperform traditional methods in all metrics, albeit at considerably higher computational costs, highlighting a trade-off between accuracy and efficiency. Additionally, LLMs better handle genre-specific challenges such as poetry and temporal variations (i.e., pre-1920 versus post-1920 texts), demonstrating that their contextual learning capabilities can advance NLP approaches to historical texts by reducing the need for domain-specific training data.</abstract>
<identifier type="citekey">fang-etal-2025-comparative</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.1</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.1/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950
%A Fang, Zhao
%A Wu, Liang-Chun
%A Kong, Xuening
%A Stewart, Spencer Dean
%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 fang-etal-2025-comparative
%X This paper compares large language models (LLMs) and traditional natural language processing (NLP) tools for performing word segmentation, part-of-speech (POS) tagging, and named entity recognition (NER) on Chinese texts from 1900 to 1950. Historical Chinese documents pose challenges for text analysis due to their logographic script, the absence of natural word boundaries, and significant linguistic changes. Using a sample dataset from the Shanghai Library Republican Journal corpus, traditional tools such as Jieba and spaCy are compared to LLMs, including GPT-4o, Claude 3.5, and the GLM series. The results show that LLMs outperform traditional methods in all metrics, albeit at considerably higher computational costs, highlighting a trade-off between accuracy and efficiency. Additionally, LLMs better handle genre-specific challenges such as poetry and temporal variations (i.e., pre-1920 versus post-1920 texts), demonstrating that their contextual learning capabilities can advance NLP approaches to historical texts by reducing the need for domain-specific training data.
%R 10.18653/v1/2025.nlp4dh-1.1
%U https://aclanthology.org/2025.nlp4dh-1.1/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.1
%P 1-6
Markdown (Informal)
[A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950](https://aclanthology.org/2025.nlp4dh-1.1/) (Fang et al., NLP4DH 2025)
ACL