@inproceedings{nikolaidis-etal-2026-cross,
title = "Cross-lingual Clustering of News Stories using Embeddings-based Community Detection",
author = "Nikolaidis, Nikolaos and
Kovacikova, Kristina and
Androutsopoulos, Ion",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.104/",
pages = "2124--2146",
ISBN = "979-8-89176-462-0",
abstract = "The widespread adoption of Large Language Models has accelerated news content generation, yet methods to help readers contextualize and responsibly consume news content lag behind. Existing approaches to clustering news articles face significant limitations. Methods based on dense representations often struggle with robustness and efficiency, while those based on sparse (n-gram) representations are unsuitable for cross-lingual applications. Additionally, LLM-based methods are expensive to apply at the needed scale, restricting their use to only well funded organizations.\par We present a novel method for efficient clustering of news articles using cross-lingual, sentence-level embeddings and community detection on similarity graphs. Our method can construct a document-level similarity graph from sentence-level embeddings, avoiding the use of sub-optimal embeddings of entire documents. The proposed method can be executed on consumer hardware, enabling practical news analysis for personal use and research.\par We also release a manually curated dataset of clustered news articles, providing a valuable resource for future research. We use the dataset to benchmark our method using nine text embedding models with cross-lingual capability and propose various practical configurations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolaidis-etal-2026-cross">
<titleInfo>
<title>Cross-lingual Clustering of News Stories using Embeddings-based Community Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Nikolaidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Kovacikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The widespread adoption of Large Language Models has accelerated news content generation, yet methods to help readers contextualize and responsibly consume news content lag behind. Existing approaches to clustering news articles face significant limitations. Methods based on dense representations often struggle with robustness and efficiency, while those based on sparse (n-gram) representations are unsuitable for cross-lingual applications. Additionally, LLM-based methods are expensive to apply at the needed scale, restricting their use to only well funded organizations.\par We present a novel method for efficient clustering of news articles using cross-lingual, sentence-level embeddings and community detection on similarity graphs. Our method can construct a document-level similarity graph from sentence-level embeddings, avoiding the use of sub-optimal embeddings of entire documents. The proposed method can be executed on consumer hardware, enabling practical news analysis for personal use and research.\par We also release a manually curated dataset of clustered news articles, providing a valuable resource for future research. We use the dataset to benchmark our method using nine text embedding models with cross-lingual capability and propose various practical configurations.</abstract>
<identifier type="citekey">nikolaidis-etal-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.104/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2124</start>
<end>2146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Clustering of News Stories using Embeddings-based Community Detection
%A Nikolaidis, Nikolaos
%A Kovacikova, Kristina
%A Androutsopoulos, Ion
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F nikolaidis-etal-2026-cross
%X The widespread adoption of Large Language Models has accelerated news content generation, yet methods to help readers contextualize and responsibly consume news content lag behind. Existing approaches to clustering news articles face significant limitations. Methods based on dense representations often struggle with robustness and efficiency, while those based on sparse (n-gram) representations are unsuitable for cross-lingual applications. Additionally, LLM-based methods are expensive to apply at the needed scale, restricting their use to only well funded organizations.\par We present a novel method for efficient clustering of news articles using cross-lingual, sentence-level embeddings and community detection on similarity graphs. Our method can construct a document-level similarity graph from sentence-level embeddings, avoiding the use of sub-optimal embeddings of entire documents. The proposed method can be executed on consumer hardware, enabling practical news analysis for personal use and research.\par We also release a manually curated dataset of clustered news articles, providing a valuable resource for future research. We use the dataset to benchmark our method using nine text embedding models with cross-lingual capability and propose various practical configurations.
%U https://aclanthology.org/2026.findings-emnlp.104/
%P 2124-2146
Markdown (Informal)
[Cross-lingual Clustering of News Stories using Embeddings-based Community Detection](https://aclanthology.org/2026.findings-emnlp.104/) (Nikolaidis et al., Findings 2026)
ACL