@inproceedings{yue-etal-2026-mooc,
title = "{MOOC}-{MESE}: Dataset and Framework for Multimodal Entity Set Expansion in {MOOC}s",
author = "Yue, Shichao and
Wan, Jing and
Chen, Yubin",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.215/",
pages = "4249--4258",
ISBN = "979-8-89176-444-6",
abstract = "Entity Set Expansion (ESE) aims to expand entities belonging to the same semantic category given only a small set of seed entities. Traditional ESE methods are primarily text-based and struggle to address two key challenges in MOOC scenarios: (1) Multimodal Semantic Dependency; (2) Generalization Issues.To facilitate research in this area, we construct MOOC-MESE, the first Chinese multimodal ESE dataset for MOOCs, which contains over 45k aligned image-text pairs. The dataset provides rich multimodal semantic information for entity expansion research in educational scenarios. Furthermore, we propose GMRM (Generative Multimodal Retrieval Model), a multimodal ESE framework that reformulates the task as a multimodal generative retrieval problem. By achieving multimodal alignment and fully exploiting cross-modal semantics, GMRM effectively mitigates generalization issues. Extensive experiments and analyses on MOOC-MESE demonstrate both the high quality of the dataset and the effectiveness of GMRM. The code is publicly available at: https://github.com/constantinus-xi/mooc-mese."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yue-etal-2026-mooc">
<titleInfo>
<title>MOOC-MESE: Dataset and Framework for Multimodal Entity Set Expansion in MOOCs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shichao</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Entity Set Expansion (ESE) aims to expand entities belonging to the same semantic category given only a small set of seed entities. Traditional ESE methods are primarily text-based and struggle to address two key challenges in MOOC scenarios: (1) Multimodal Semantic Dependency; (2) Generalization Issues.To facilitate research in this area, we construct MOOC-MESE, the first Chinese multimodal ESE dataset for MOOCs, which contains over 45k aligned image-text pairs. The dataset provides rich multimodal semantic information for entity expansion research in educational scenarios. Furthermore, we propose GMRM (Generative Multimodal Retrieval Model), a multimodal ESE framework that reformulates the task as a multimodal generative retrieval problem. By achieving multimodal alignment and fully exploiting cross-modal semantics, GMRM effectively mitigates generalization issues. Extensive experiments and analyses on MOOC-MESE demonstrate both the high quality of the dataset and the effectiveness of GMRM. The code is publicly available at: https://github.com/constantinus-xi/mooc-mese.</abstract>
<identifier type="citekey">yue-etal-2026-mooc</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.215/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4249</start>
<end>4258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOOC-MESE: Dataset and Framework for Multimodal Entity Set Expansion in MOOCs
%A Yue, Shichao
%A Wan, Jing
%A Chen, Yubin
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F yue-etal-2026-mooc
%X Entity Set Expansion (ESE) aims to expand entities belonging to the same semantic category given only a small set of seed entities. Traditional ESE methods are primarily text-based and struggle to address two key challenges in MOOC scenarios: (1) Multimodal Semantic Dependency; (2) Generalization Issues.To facilitate research in this area, we construct MOOC-MESE, the first Chinese multimodal ESE dataset for MOOCs, which contains over 45k aligned image-text pairs. The dataset provides rich multimodal semantic information for entity expansion research in educational scenarios. Furthermore, we propose GMRM (Generative Multimodal Retrieval Model), a multimodal ESE framework that reformulates the task as a multimodal generative retrieval problem. By achieving multimodal alignment and fully exploiting cross-modal semantics, GMRM effectively mitigates generalization issues. Extensive experiments and analyses on MOOC-MESE demonstrate both the high quality of the dataset and the effectiveness of GMRM. The code is publicly available at: https://github.com/constantinus-xi/mooc-mese.
%U https://aclanthology.org/2026.findings-aacl.215/
%P 4249-4258
Markdown (Informal)
[MOOC-MESE: Dataset and Framework for Multimodal Entity Set Expansion in MOOCs](https://aclanthology.org/2026.findings-aacl.215/) (Yue et al., Findings 2026)
ACL