@inproceedings{nie-etal-2024-stspl,
title = "{STSPL}-{SSC}: Semi-Supervised Few-Shot Short Text Clustering with Semantic text similarity Optimized Pseudo-Labels",
author = "Nie, Wenhua and
Deng, Lin and
Liu, Chang-Bo and
Wei, Jialing and
Han, Ruitong and
Zheng, Haoran",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.725/",
doi = "10.18653/v1/2024.findings-acl.725",
pages = "12174--12185",
abstract = "This study introduces the Semantic Textual Similarity Pseudo-Label Semi-Supervised Clustering (STSPL-SSC) framework. The STSPL-SSC framework is designed to tackle the prevalent issue of scarce labeled data by combining a Semantic Textual Similarity Pseudo-Label Generation process with a Robust Contrastive Learning module. The process begins with employing k-means clustering on embeddings for initial pseudo-Label allocation. Then we use a Semantic Text Similarity-enhanced module to supervise the secondary clustering of pseudo-labels using labeled data to better align with the real clustering centers. Subsequently, an Adaptive Optimal Transport (AOT) approach fine-tunes the pseudo-labels. Finally, a Robust Contrastive Learning module is employed to foster the learning of classification and instance-level distinctions, aiding clusters to better separate. Experiments conducted on multiple real-world datasets demonstrate that with just one label per class, clustering performance can be significantly improved, outperforming state-of-the-art models with an increase of 1-6{\%} in both accuracy and normalized mutual information, approaching the results of fully-labeled classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nie-etal-2024-stspl">
<titleInfo>
<title>STSPL-SSC: Semi-Supervised Few-Shot Short Text Clustering with Semantic text similarity Optimized Pseudo-Labels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhua</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang-Bo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialing</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruitong</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study introduces the Semantic Textual Similarity Pseudo-Label Semi-Supervised Clustering (STSPL-SSC) framework. The STSPL-SSC framework is designed to tackle the prevalent issue of scarce labeled data by combining a Semantic Textual Similarity Pseudo-Label Generation process with a Robust Contrastive Learning module. The process begins with employing k-means clustering on embeddings for initial pseudo-Label allocation. Then we use a Semantic Text Similarity-enhanced module to supervise the secondary clustering of pseudo-labels using labeled data to better align with the real clustering centers. Subsequently, an Adaptive Optimal Transport (AOT) approach fine-tunes the pseudo-labels. Finally, a Robust Contrastive Learning module is employed to foster the learning of classification and instance-level distinctions, aiding clusters to better separate. Experiments conducted on multiple real-world datasets demonstrate that with just one label per class, clustering performance can be significantly improved, outperforming state-of-the-art models with an increase of 1-6% in both accuracy and normalized mutual information, approaching the results of fully-labeled classification.</abstract>
<identifier type="citekey">nie-etal-2024-stspl</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.725</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.725/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12174</start>
<end>12185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STSPL-SSC: Semi-Supervised Few-Shot Short Text Clustering with Semantic text similarity Optimized Pseudo-Labels
%A Nie, Wenhua
%A Deng, Lin
%A Liu, Chang-Bo
%A Wei, Jialing
%A Han, Ruitong
%A Zheng, Haoran
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F nie-etal-2024-stspl
%X This study introduces the Semantic Textual Similarity Pseudo-Label Semi-Supervised Clustering (STSPL-SSC) framework. The STSPL-SSC framework is designed to tackle the prevalent issue of scarce labeled data by combining a Semantic Textual Similarity Pseudo-Label Generation process with a Robust Contrastive Learning module. The process begins with employing k-means clustering on embeddings for initial pseudo-Label allocation. Then we use a Semantic Text Similarity-enhanced module to supervise the secondary clustering of pseudo-labels using labeled data to better align with the real clustering centers. Subsequently, an Adaptive Optimal Transport (AOT) approach fine-tunes the pseudo-labels. Finally, a Robust Contrastive Learning module is employed to foster the learning of classification and instance-level distinctions, aiding clusters to better separate. Experiments conducted on multiple real-world datasets demonstrate that with just one label per class, clustering performance can be significantly improved, outperforming state-of-the-art models with an increase of 1-6% in both accuracy and normalized mutual information, approaching the results of fully-labeled classification.
%R 10.18653/v1/2024.findings-acl.725
%U https://aclanthology.org/2024.findings-acl.725/
%U https://doi.org/10.18653/v1/2024.findings-acl.725
%P 12174-12185
Markdown (Informal)
[STSPL-SSC: Semi-Supervised Few-Shot Short Text Clustering with Semantic text similarity Optimized Pseudo-Labels](https://aclanthology.org/2024.findings-acl.725/) (Nie et al., Findings 2024)
ACL