@inproceedings{zheng-etal-2025-fnscc,
title = "{FNSCC}: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text",
author = "Zheng, Zijian and
Lu, Yonghe and
Yin, Jian",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.154/",
doi = "10.18653/v1/2025.findings-emnlp.154",
pages = "2831--2846",
ISBN = "979-8-89176-335-7",
abstract = "Short texts pose significant challenges for clustering due to semantic sparsity, limited context, and fuzzy category boundaries. Although recent contrastive learning methods improve instance-level representation, they often overlook local semantic structure within the clustering head. Moreover, treating semantically similar neighbors as negatives impair cluster-level discrimination. To address these issues, we propose Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering (FNSCC) framework. FNSCC incorporates neighborhood information at both the instance-level and cluster-level. At the instance-level, it excludes neighbors from the negative sample set to enhance inter-cluster separability. At the cluster-level, it introduces fuzzy neighborhood-aware weighting to refine soft assignment probabilities, encouraging alignment with semantically coherent clusters. Experiments on multiple benchmark short text datasets demonstrate that FNSCC consistently outperforms state-of-the-art models in accuracy and normalized mutual information. Our code is available at \url{https://github.com/zjzone/FNSCC}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2025-fnscc">
<titleInfo>
<title>FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zijian</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonghe</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Short texts pose significant challenges for clustering due to semantic sparsity, limited context, and fuzzy category boundaries. Although recent contrastive learning methods improve instance-level representation, they often overlook local semantic structure within the clustering head. Moreover, treating semantically similar neighbors as negatives impair cluster-level discrimination. To address these issues, we propose Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering (FNSCC) framework. FNSCC incorporates neighborhood information at both the instance-level and cluster-level. At the instance-level, it excludes neighbors from the negative sample set to enhance inter-cluster separability. At the cluster-level, it introduces fuzzy neighborhood-aware weighting to refine soft assignment probabilities, encouraging alignment with semantically coherent clusters. Experiments on multiple benchmark short text datasets demonstrate that FNSCC consistently outperforms state-of-the-art models in accuracy and normalized mutual information. Our code is available at https://github.com/zjzone/FNSCC.</abstract>
<identifier type="citekey">zheng-etal-2025-fnscc</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.154</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.154/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2831</start>
<end>2846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text
%A Zheng, Zijian
%A Lu, Yonghe
%A Yin, Jian
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zheng-etal-2025-fnscc
%X Short texts pose significant challenges for clustering due to semantic sparsity, limited context, and fuzzy category boundaries. Although recent contrastive learning methods improve instance-level representation, they often overlook local semantic structure within the clustering head. Moreover, treating semantically similar neighbors as negatives impair cluster-level discrimination. To address these issues, we propose Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering (FNSCC) framework. FNSCC incorporates neighborhood information at both the instance-level and cluster-level. At the instance-level, it excludes neighbors from the negative sample set to enhance inter-cluster separability. At the cluster-level, it introduces fuzzy neighborhood-aware weighting to refine soft assignment probabilities, encouraging alignment with semantically coherent clusters. Experiments on multiple benchmark short text datasets demonstrate that FNSCC consistently outperforms state-of-the-art models in accuracy and normalized mutual information. Our code is available at https://github.com/zjzone/FNSCC.
%R 10.18653/v1/2025.findings-emnlp.154
%U https://aclanthology.org/2025.findings-emnlp.154/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.154
%P 2831-2846
Markdown (Informal)
[FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text](https://aclanthology.org/2025.findings-emnlp.154/) (Zheng et al., Findings 2025)
ACL