@inproceedings{fang-etal-2024-cwtm,
title = "{CWTM}: Leveraging Contextualized Word Embeddings from {BERT} for Neural Topic Modeling",
author = "Fang, Zheng and
He, Yulan and
Procter, Rob",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.382",
pages = "4273--4286",
abstract = "Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualized word embeddings, however, show superiority in word sense disambiguation and effectively address the OOV issue. In this work, we introduce a novel neural topic model called the Contextlized Word Topic Model (CWTM), which integrates contextualized word embeddings from BERT. The model is capable of learning the topic vector of a document without BOW information. In addition, it can also derive the topic vectors for individual words within a document based on their contextualized word embeddings. Experiments across various datasets show that CWTM generates more coherent and meaningful topics compared to existing topic models, while also accommodating unseen words in newly encountered documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2024-cwtm">
<titleInfo>
<title>CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">Procter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualized word embeddings, however, show superiority in word sense disambiguation and effectively address the OOV issue. In this work, we introduce a novel neural topic model called the Contextlized Word Topic Model (CWTM), which integrates contextualized word embeddings from BERT. The model is capable of learning the topic vector of a document without BOW information. In addition, it can also derive the topic vectors for individual words within a document based on their contextualized word embeddings. Experiments across various datasets show that CWTM generates more coherent and meaningful topics compared to existing topic models, while also accommodating unseen words in newly encountered documents.</abstract>
<identifier type="citekey">fang-etal-2024-cwtm</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.382</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4273</start>
<end>4286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling
%A Fang, Zheng
%A He, Yulan
%A Procter, Rob
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F fang-etal-2024-cwtm
%X Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualized word embeddings, however, show superiority in word sense disambiguation and effectively address the OOV issue. In this work, we introduce a novel neural topic model called the Contextlized Word Topic Model (CWTM), which integrates contextualized word embeddings from BERT. The model is capable of learning the topic vector of a document without BOW information. In addition, it can also derive the topic vectors for individual words within a document based on their contextualized word embeddings. Experiments across various datasets show that CWTM generates more coherent and meaningful topics compared to existing topic models, while also accommodating unseen words in newly encountered documents.
%U https://aclanthology.org/2024.lrec-main.382
%P 4273-4286
Markdown (Informal)
[CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling](https://aclanthology.org/2024.lrec-main.382) (Fang et al., LREC-COLING 2024)
ACL