@inproceedings{mukherjee-etal-2022-topic,
title = "Topic-aware Multimodal Summarization",
author = "Mukherjee, Sourajit and
Jangra, Anubhav and
Saha, Sriparna and
Jatowt, Adam",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.36",
pages = "387--398",
abstract = "Multimodal Summarization (MS) has attracted research interest in the past few years due to the ease with which users perceive multimodal summaries. It is important for MS models to consider the topic a given target content belongs to. In the current paper, we propose a topic-aware MS system which performs two tasks simultaneously: differentiating the images into {``}on-topic{''} and {``}off-topic{''} categories and further utilizing the {``}on-topic{''} images to generate multimodal summaries. The hypothesis is that, the proposed topic similarity classifier will help in generating better multimodal summary by focusing on important components of images and text which are specific to a particular topic. To develop the topic similarity classifier, we have augmented the existing popular MS data set, MSMO, with similar {``}on-topic{''} and dissimilar {``}off-topic{''} images for each sample. Our experimental results establish that the focus on {``}on-topic{''} features helps in generating topic-aware multimodal summaries, which outperforms the state of the art approach by 1.7 {\%} in ROUGE-L metric.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukherjee-etal-2022-topic">
<titleInfo>
<title>Topic-aware Multimodal Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sourajit</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Jangra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Jatowt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Summarization (MS) has attracted research interest in the past few years due to the ease with which users perceive multimodal summaries. It is important for MS models to consider the topic a given target content belongs to. In the current paper, we propose a topic-aware MS system which performs two tasks simultaneously: differentiating the images into “on-topic” and “off-topic” categories and further utilizing the “on-topic” images to generate multimodal summaries. The hypothesis is that, the proposed topic similarity classifier will help in generating better multimodal summary by focusing on important components of images and text which are specific to a particular topic. To develop the topic similarity classifier, we have augmented the existing popular MS data set, MSMO, with similar “on-topic” and dissimilar “off-topic” images for each sample. Our experimental results establish that the focus on “on-topic” features helps in generating topic-aware multimodal summaries, which outperforms the state of the art approach by 1.7 % in ROUGE-L metric.</abstract>
<identifier type="citekey">mukherjee-etal-2022-topic</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.36</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>387</start>
<end>398</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic-aware Multimodal Summarization
%A Mukherjee, Sourajit
%A Jangra, Anubhav
%A Saha, Sriparna
%A Jatowt, Adam
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F mukherjee-etal-2022-topic
%X Multimodal Summarization (MS) has attracted research interest in the past few years due to the ease with which users perceive multimodal summaries. It is important for MS models to consider the topic a given target content belongs to. In the current paper, we propose a topic-aware MS system which performs two tasks simultaneously: differentiating the images into “on-topic” and “off-topic” categories and further utilizing the “on-topic” images to generate multimodal summaries. The hypothesis is that, the proposed topic similarity classifier will help in generating better multimodal summary by focusing on important components of images and text which are specific to a particular topic. To develop the topic similarity classifier, we have augmented the existing popular MS data set, MSMO, with similar “on-topic” and dissimilar “off-topic” images for each sample. Our experimental results establish that the focus on “on-topic” features helps in generating topic-aware multimodal summaries, which outperforms the state of the art approach by 1.7 % in ROUGE-L metric.
%U https://aclanthology.org/2022.findings-aacl.36
%P 387-398
Markdown (Informal)
[Topic-aware Multimodal Summarization](https://aclanthology.org/2022.findings-aacl.36) (Mukherjee et al., Findings 2022)
ACL
- Sourajit Mukherjee, Anubhav Jangra, Sriparna Saha, and Adam Jatowt. 2022. Topic-aware Multimodal Summarization. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 387–398, Online only. Association for Computational Linguistics.