@inproceedings{li-etal-2026-stream,
title = "{STREAM}-{ZH}: Simplified Topic Retrieval Exploration and Analysis Module for {C}hinese Language",
author = "Li, Hongyi and
Lian, Jianjun and
Thielmann, Anton Frederik and
Python, Andre",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-short.28/",
pages = "371--383",
ISBN = "979-8-89176-381-4",
abstract = "We introduce Simplified Topic Retrieval Exploration and Analysis Module for Chinese language (STREAM-ZH), the first topic modeling package to fully support the Chinese language across a broad range of topic models, evaluation metrics, and preprocessing workflows. Tailored to both simplified and traditional Chinese language, our package extends the STREAM topic modeling framework with a curated collection of preprocessed textual datasets in Chinese from which we assess the performance of classical, neural, and clustering topic models using commonly-used intruder, diversity, and coherence metrics. The results of a benchmark analysis bring evidence that within our framework, topic models may generate coherent and diverse topics from datasets in Chinese language, outperforming those generated by topic models using English-translated textual input. Our framework facilitates multilingual accessibility and research in topic modeling applied to Chinese textual data. The code is available at the following link: https://github.com/AnFreTh/STREAM"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-stream">
<titleInfo>
<title>STREAM-ZH: Simplified Topic Retrieval Exploration and Analysis Module for Chinese Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianjun</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="given">Frederik</namePart>
<namePart type="family">Thielmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Python</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-381-4</identifier>
</relatedItem>
<abstract>We introduce Simplified Topic Retrieval Exploration and Analysis Module for Chinese language (STREAM-ZH), the first topic modeling package to fully support the Chinese language across a broad range of topic models, evaluation metrics, and preprocessing workflows. Tailored to both simplified and traditional Chinese language, our package extends the STREAM topic modeling framework with a curated collection of preprocessed textual datasets in Chinese from which we assess the performance of classical, neural, and clustering topic models using commonly-used intruder, diversity, and coherence metrics. The results of a benchmark analysis bring evidence that within our framework, topic models may generate coherent and diverse topics from datasets in Chinese language, outperforming those generated by topic models using English-translated textual input. Our framework facilitates multilingual accessibility and research in topic modeling applied to Chinese textual data. The code is available at the following link: https://github.com/AnFreTh/STREAM</abstract>
<identifier type="citekey">li-etal-2026-stream</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-short.28/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>371</start>
<end>383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STREAM-ZH: Simplified Topic Retrieval Exploration and Analysis Module for Chinese Language
%A Li, Hongyi
%A Lian, Jianjun
%A Thielmann, Anton Frederik
%A Python, Andre
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-381-4
%F li-etal-2026-stream
%X We introduce Simplified Topic Retrieval Exploration and Analysis Module for Chinese language (STREAM-ZH), the first topic modeling package to fully support the Chinese language across a broad range of topic models, evaluation metrics, and preprocessing workflows. Tailored to both simplified and traditional Chinese language, our package extends the STREAM topic modeling framework with a curated collection of preprocessed textual datasets in Chinese from which we assess the performance of classical, neural, and clustering topic models using commonly-used intruder, diversity, and coherence metrics. The results of a benchmark analysis bring evidence that within our framework, topic models may generate coherent and diverse topics from datasets in Chinese language, outperforming those generated by topic models using English-translated textual input. Our framework facilitates multilingual accessibility and research in topic modeling applied to Chinese textual data. The code is available at the following link: https://github.com/AnFreTh/STREAM
%U https://aclanthology.org/2026.eacl-short.28/
%P 371-383
Markdown (Informal)
[STREAM-ZH: Simplified Topic Retrieval Exploration and Analysis Module for Chinese Language](https://aclanthology.org/2026.eacl-short.28/) (Li et al., EACL 2026)
ACL