@inproceedings{yin-etal-2022-improving,
title = "Improving Deep Embedded Clustering via Learning Cluster-level Representations",
author = "Yin, Qing and
Wang, Zhihua and
Song, Yunya and
Xu, Yida and
Niu, Shuai and
Bai, Liang and
Guo, Yike and
Yang, Xian",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.195",
pages = "2226--2236",
abstract = "Driven by recent advances in neural networks, various Deep Embedding Clustering (DEC) based short text clustering models are being developed. In these works, latent representation learning and text clustering are performed simultaneously. Although these methods are becoming increasingly popular, they use pure cluster-oriented objectives, which can produce meaningless representations. To alleviate this problem, several improvements have been developed to introduce additional learning objectives in the clustering process, such as models based on contrastive learning. However, existing efforts rely heavily on learning meaningful representations at the instance level. They have limited focus on learning global representations, which are necessary to capture the overall data structure at the cluster level. In this paper, we propose a novel DEC model, which we named the deep embedded clustering model with cluster-level representation learning (DECCRL) to jointly learn cluster and instance level representations. Here, we extend the embedded topic modelling approach to introduce reconstruction constraints to help learn cluster-level representations. Experimental results on real-world short text datasets demonstrate that our model produces meaningful clusters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2022-improving">
<titleInfo>
<title>Improving Deep Embedded Clustering via Learning Cluster-level Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunya</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yida</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yike</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Driven by recent advances in neural networks, various Deep Embedding Clustering (DEC) based short text clustering models are being developed. In these works, latent representation learning and text clustering are performed simultaneously. Although these methods are becoming increasingly popular, they use pure cluster-oriented objectives, which can produce meaningless representations. To alleviate this problem, several improvements have been developed to introduce additional learning objectives in the clustering process, such as models based on contrastive learning. However, existing efforts rely heavily on learning meaningful representations at the instance level. They have limited focus on learning global representations, which are necessary to capture the overall data structure at the cluster level. In this paper, we propose a novel DEC model, which we named the deep embedded clustering model with cluster-level representation learning (DECCRL) to jointly learn cluster and instance level representations. Here, we extend the embedded topic modelling approach to introduce reconstruction constraints to help learn cluster-level representations. Experimental results on real-world short text datasets demonstrate that our model produces meaningful clusters.</abstract>
<identifier type="citekey">yin-etal-2022-improving</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.195</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>2226</start>
<end>2236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Deep Embedded Clustering via Learning Cluster-level Representations
%A Yin, Qing
%A Wang, Zhihua
%A Song, Yunya
%A Xu, Yida
%A Niu, Shuai
%A Bai, Liang
%A Guo, Yike
%A Yang, Xian
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F yin-etal-2022-improving
%X Driven by recent advances in neural networks, various Deep Embedding Clustering (DEC) based short text clustering models are being developed. In these works, latent representation learning and text clustering are performed simultaneously. Although these methods are becoming increasingly popular, they use pure cluster-oriented objectives, which can produce meaningless representations. To alleviate this problem, several improvements have been developed to introduce additional learning objectives in the clustering process, such as models based on contrastive learning. However, existing efforts rely heavily on learning meaningful representations at the instance level. They have limited focus on learning global representations, which are necessary to capture the overall data structure at the cluster level. In this paper, we propose a novel DEC model, which we named the deep embedded clustering model with cluster-level representation learning (DECCRL) to jointly learn cluster and instance level representations. Here, we extend the embedded topic modelling approach to introduce reconstruction constraints to help learn cluster-level representations. Experimental results on real-world short text datasets demonstrate that our model produces meaningful clusters.
%U https://aclanthology.org/2022.coling-1.195
%P 2226-2236
Markdown (Informal)
[Improving Deep Embedded Clustering via Learning Cluster-level Representations](https://aclanthology.org/2022.coling-1.195) (Yin et al., COLING 2022)
ACL
- Qing Yin, Zhihua Wang, Yunya Song, Yida Xu, Shuai Niu, Liang Bai, Yike Guo, and Xian Yang. 2022. Improving Deep Embedded Clustering via Learning Cluster-level Representations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2226–2236, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.