@inproceedings{gonzalez-pizarro-carenini-2024-neural,
title = "Neural Multimodal Topic Modeling: A Comprehensive Evaluation",
author = "Gonzalez-Pizarro, Felipe and
Carenini, Giuseppe",
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.1064",
pages = "12159--12172",
abstract = "Neural topic models can successfully find coherent and diverse topics in textual data. However, they are limited in dealing with multimodal datasets (e.g., images and text). This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images. In the process, we propose two novel topic modeling solutions and two novel evaluation metrics. Overall, our evaluation on an unprecedented rich and diverse collection of datasets indicates that both of our models generate coherent and diverse topics. Nevertheless, the extent to which one method outperforms the other depends on the metrics and dataset combinations, which suggests further exploration of hybrid solutions in the future. Notably, our succinct human evaluation aligns with the outcomes determined by our proposed metrics. This alignment not only reinforces the credibility of our metrics but also highlights the potential for their application in guiding future multimodal topic modeling endeavors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-pizarro-carenini-2024-neural">
<titleInfo>
<title>Neural Multimodal Topic Modeling: A Comprehensive Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Gonzalez-Pizarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</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>Neural topic models can successfully find coherent and diverse topics in textual data. However, they are limited in dealing with multimodal datasets (e.g., images and text). This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images. In the process, we propose two novel topic modeling solutions and two novel evaluation metrics. Overall, our evaluation on an unprecedented rich and diverse collection of datasets indicates that both of our models generate coherent and diverse topics. Nevertheless, the extent to which one method outperforms the other depends on the metrics and dataset combinations, which suggests further exploration of hybrid solutions in the future. Notably, our succinct human evaluation aligns with the outcomes determined by our proposed metrics. This alignment not only reinforces the credibility of our metrics but also highlights the potential for their application in guiding future multimodal topic modeling endeavors.</abstract>
<identifier type="citekey">gonzalez-pizarro-carenini-2024-neural</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1064</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12159</start>
<end>12172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Multimodal Topic Modeling: A Comprehensive Evaluation
%A Gonzalez-Pizarro, Felipe
%A Carenini, Giuseppe
%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 gonzalez-pizarro-carenini-2024-neural
%X Neural topic models can successfully find coherent and diverse topics in textual data. However, they are limited in dealing with multimodal datasets (e.g., images and text). This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images. In the process, we propose two novel topic modeling solutions and two novel evaluation metrics. Overall, our evaluation on an unprecedented rich and diverse collection of datasets indicates that both of our models generate coherent and diverse topics. Nevertheless, the extent to which one method outperforms the other depends on the metrics and dataset combinations, which suggests further exploration of hybrid solutions in the future. Notably, our succinct human evaluation aligns with the outcomes determined by our proposed metrics. This alignment not only reinforces the credibility of our metrics but also highlights the potential for their application in guiding future multimodal topic modeling endeavors.
%U https://aclanthology.org/2024.lrec-main.1064
%P 12159-12172
Markdown (Informal)
[Neural Multimodal Topic Modeling: A Comprehensive Evaluation](https://aclanthology.org/2024.lrec-main.1064) (Gonzalez-Pizarro & Carenini, LREC-COLING 2024)
ACL
- Felipe Gonzalez-Pizarro and Giuseppe Carenini. 2024. Neural Multimodal Topic Modeling: A Comprehensive Evaluation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12159–12172, Torino, Italia. ELRA and ICCL.