@inproceedings{zhuang-etal-2024-automatic,
title = "Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output",
author = "Zhuang, Haojie and
Zhang, Wei Emma and
Xie, Leon and
Chen, Weitong and
Yang, Jian and
Sheng, Quan",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.430",
doi = "10.18653/v1/2024.naacl-long.430",
pages = "7768--7790",
abstract = "Multimodal summarization with multimodal output (MSMO) has attracted increasing research interests recently as multimodal summary could provide more comprehensive information compared to text-only summary, effectively improving the user experience and satisfaction. As one of the most fundamental components for the development of MSMO, evaluation is an emerging yet underexplored research topic. In this paper, we fill this gap and propose a research framework that studies three research questions of MSMO evaluation: (1) Automatic Evaluation: We propose a novel metric mLLM-EVAL, which utilizes multimodal Large Language Model for MSMO EVALuation. (2) Meta-Evaluation: We create a meta-evaluation benchmark dataset by collecting human-annotated scores for multimodal summaries. With our benchmark, we conduct meta-evaluation analysis to assess the quality of different evaluation metrics and show the effectiveness of our proposed mLLM-EVAL. (3) Human Evaluation: To provide more objective and unbiased human annotations for meta-evaluation, we hypothesize and verify three types of cognitive biases in human evaluation. We also incorporate our findings into the human annotation process in the meta-evaluation benchmark. Overall, our research framework provides an evaluation metric, a meta-evaluation benchmark dataset annotated by humans and an analysis of cognitive biases in human evaluation, which we believe would serve as a valuable and comprehensive resource for the MSMO research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhuang-etal-2024-automatic">
<titleInfo>
<title>Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haojie</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="given">Emma</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weitong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal summarization with multimodal output (MSMO) has attracted increasing research interests recently as multimodal summary could provide more comprehensive information compared to text-only summary, effectively improving the user experience and satisfaction. As one of the most fundamental components for the development of MSMO, evaluation is an emerging yet underexplored research topic. In this paper, we fill this gap and propose a research framework that studies three research questions of MSMO evaluation: (1) Automatic Evaluation: We propose a novel metric mLLM-EVAL, which utilizes multimodal Large Language Model for MSMO EVALuation. (2) Meta-Evaluation: We create a meta-evaluation benchmark dataset by collecting human-annotated scores for multimodal summaries. With our benchmark, we conduct meta-evaluation analysis to assess the quality of different evaluation metrics and show the effectiveness of our proposed mLLM-EVAL. (3) Human Evaluation: To provide more objective and unbiased human annotations for meta-evaluation, we hypothesize and verify three types of cognitive biases in human evaluation. We also incorporate our findings into the human annotation process in the meta-evaluation benchmark. Overall, our research framework provides an evaluation metric, a meta-evaluation benchmark dataset annotated by humans and an analysis of cognitive biases in human evaluation, which we believe would serve as a valuable and comprehensive resource for the MSMO research community.</abstract>
<identifier type="citekey">zhuang-etal-2024-automatic</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.430</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.430</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7768</start>
<end>7790</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output
%A Zhuang, Haojie
%A Zhang, Wei Emma
%A Xie, Leon
%A Chen, Weitong
%A Yang, Jian
%A Sheng, Quan
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhuang-etal-2024-automatic
%X Multimodal summarization with multimodal output (MSMO) has attracted increasing research interests recently as multimodal summary could provide more comprehensive information compared to text-only summary, effectively improving the user experience and satisfaction. As one of the most fundamental components for the development of MSMO, evaluation is an emerging yet underexplored research topic. In this paper, we fill this gap and propose a research framework that studies three research questions of MSMO evaluation: (1) Automatic Evaluation: We propose a novel metric mLLM-EVAL, which utilizes multimodal Large Language Model for MSMO EVALuation. (2) Meta-Evaluation: We create a meta-evaluation benchmark dataset by collecting human-annotated scores for multimodal summaries. With our benchmark, we conduct meta-evaluation analysis to assess the quality of different evaluation metrics and show the effectiveness of our proposed mLLM-EVAL. (3) Human Evaluation: To provide more objective and unbiased human annotations for meta-evaluation, we hypothesize and verify three types of cognitive biases in human evaluation. We also incorporate our findings into the human annotation process in the meta-evaluation benchmark. Overall, our research framework provides an evaluation metric, a meta-evaluation benchmark dataset annotated by humans and an analysis of cognitive biases in human evaluation, which we believe would serve as a valuable and comprehensive resource for the MSMO research community.
%R 10.18653/v1/2024.naacl-long.430
%U https://aclanthology.org/2024.naacl-long.430
%U https://doi.org/10.18653/v1/2024.naacl-long.430
%P 7768-7790
Markdown (Informal)
[Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output](https://aclanthology.org/2024.naacl-long.430) (Zhuang et al., NAACL 2024)
ACL