@inproceedings{tseng-etal-2026-capturing,
title = "Capturing {A}ncient {C}hinese Sense Induction with Automatic Pipelines",
author = "Tseng, Guan-Yu and
Lim, Chunki and
Lin, Chih-Han and
Pan, Tung-Le and
Wang, Yu-Chieh and
Yeh, Lang-Ching and
Hsieh, Shu-Kai",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.15/",
doi = "10.63317/4ku4whfwarht",
pages = "163--176",
abstract = "While the study of diachronic semantic change has advanced alongside recent computational developments, structured lexical resources that reflect semantic evolution remain scarce for many languages, including Ancient Chinese. By systematizing the diachronic transformations within the Chinese Text Project (ctext, a large corpus of Ancient Chinese), we aim to bridge the gap between traditional philological inquiry and contemporary computational linguistics. This study proposes a pipeline that extracts contextualized embeddings from GujiBERT-fan, a language model pre-trained on pre-modern Chinese, and applies dynamic hierarchical clustering to identify distinct senses across historical periods. The pipeline operates at two levels: a global clustering that aggregates data across all periods to capture the full semantic space, and local clustering within each dynasty to reveal period-specific usage patterns. We test the pipeline with a pilot study on the character 手 (shǒu, ``hand'') across eight dynastic periods, covering over 185,000 occurrences. The results show that the pipeline can capture the diachronic shift from concrete to abstract senses, demonstrating its potential as a scalable method for mapping semantic evolution in historical languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tseng-etal-2026-capturing">
<titleInfo>
<title>Capturing Ancient Chinese Sense Induction with Automatic Pipelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guan-Yu</namePart>
<namePart type="family">Tseng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunki</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Han</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tung-Le</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Chieh</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lang-Ching</namePart>
<namePart type="family">Yeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu-Kai</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While the study of diachronic semantic change has advanced alongside recent computational developments, structured lexical resources that reflect semantic evolution remain scarce for many languages, including Ancient Chinese. By systematizing the diachronic transformations within the Chinese Text Project (ctext, a large corpus of Ancient Chinese), we aim to bridge the gap between traditional philological inquiry and contemporary computational linguistics. This study proposes a pipeline that extracts contextualized embeddings from GujiBERT-fan, a language model pre-trained on pre-modern Chinese, and applies dynamic hierarchical clustering to identify distinct senses across historical periods. The pipeline operates at two levels: a global clustering that aggregates data across all periods to capture the full semantic space, and local clustering within each dynasty to reveal period-specific usage patterns. We test the pipeline with a pilot study on the character 手 (shǒu, “hand”) across eight dynastic periods, covering over 185,000 occurrences. The results show that the pipeline can capture the diachronic shift from concrete to abstract senses, demonstrating its potential as a scalable method for mapping semantic evolution in historical languages.</abstract>
<identifier type="citekey">tseng-etal-2026-capturing</identifier>
<identifier type="doi">10.63317/4ku4whfwarht</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.15/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>163</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Capturing Ancient Chinese Sense Induction with Automatic Pipelines
%A Tseng, Guan-Yu
%A Lim, Chunki
%A Lin, Chih-Han
%A Pan, Tung-Le
%A Wang, Yu-Chieh
%A Yeh, Lang-Ching
%A Hsieh, Shu-Kai
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F tseng-etal-2026-capturing
%X While the study of diachronic semantic change has advanced alongside recent computational developments, structured lexical resources that reflect semantic evolution remain scarce for many languages, including Ancient Chinese. By systematizing the diachronic transformations within the Chinese Text Project (ctext, a large corpus of Ancient Chinese), we aim to bridge the gap between traditional philological inquiry and contemporary computational linguistics. This study proposes a pipeline that extracts contextualized embeddings from GujiBERT-fan, a language model pre-trained on pre-modern Chinese, and applies dynamic hierarchical clustering to identify distinct senses across historical periods. The pipeline operates at two levels: a global clustering that aggregates data across all periods to capture the full semantic space, and local clustering within each dynasty to reveal period-specific usage patterns. We test the pipeline with a pilot study on the character 手 (shǒu, “hand”) across eight dynastic periods, covering over 185,000 occurrences. The results show that the pipeline can capture the diachronic shift from concrete to abstract senses, demonstrating its potential as a scalable method for mapping semantic evolution in historical languages.
%R 10.63317/4ku4whfwarht
%U https://aclanthology.org/2026.lt4hala-1.15/
%U https://doi.org/10.63317/4ku4whfwarht
%P 163-176
Markdown (Informal)
[Capturing Ancient Chinese Sense Induction with Automatic Pipelines](https://aclanthology.org/2026.lt4hala-1.15/) (Tseng et al., LT4HALA 2026)
ACL
- Guan-Yu Tseng, Chunki Lim, Chih-Han Lin, Tung-Le Pan, Yu-Chieh Wang, Lang-Ching Yeh, and Shu-Kai Hsieh. 2026. Capturing Ancient Chinese Sense Induction with Automatic Pipelines. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 163–176, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).