@inproceedings{ren-etal-2024-grounded-multimodal,
title = "Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline",
author = "Ren, Haopeng and
Zeng, Yushi and
Cai, Yi and
Ye, Zhenqi and
Yuan, Li and
Zhu, Pinli",
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.702",
pages = "7971--7981",
abstract = "Much of commonsense knowledge in real world is the form of procudures or sequences of steps to achieve particular goals. In recent years, knowledge extraction on procedural documents has attracted considerable attention. However, they often focus on procedural text but ignore a common multimodal scenario in the real world. Images and text can complement each other semantically, alleviating the semantic ambiguity suffered in text-only modality. Motivated by these, in this paper, we explore a problem of grounded multimodal procedural entity recognition (GMPER), aiming to detect the entity and the corresponding bounding box groundings in image (i.e., visual entities). A new dataset (Wiki-GMPER) is bult and extensive experiments are conducted to evaluate the effectiveness of our proposed model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2024-grounded-multimodal">
<titleInfo>
<title>Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haopeng</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yushi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenqi</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pinli</namePart>
<namePart type="family">Zhu</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>Much of commonsense knowledge in real world is the form of procudures or sequences of steps to achieve particular goals. In recent years, knowledge extraction on procedural documents has attracted considerable attention. However, they often focus on procedural text but ignore a common multimodal scenario in the real world. Images and text can complement each other semantically, alleviating the semantic ambiguity suffered in text-only modality. Motivated by these, in this paper, we explore a problem of grounded multimodal procedural entity recognition (GMPER), aiming to detect the entity and the corresponding bounding box groundings in image (i.e., visual entities). A new dataset (Wiki-GMPER) is bult and extensive experiments are conducted to evaluate the effectiveness of our proposed model.</abstract>
<identifier type="citekey">ren-etal-2024-grounded-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.702</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7971</start>
<end>7981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline
%A Ren, Haopeng
%A Zeng, Yushi
%A Cai, Yi
%A Ye, Zhenqi
%A Yuan, Li
%A Zhu, Pinli
%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 ren-etal-2024-grounded-multimodal
%X Much of commonsense knowledge in real world is the form of procudures or sequences of steps to achieve particular goals. In recent years, knowledge extraction on procedural documents has attracted considerable attention. However, they often focus on procedural text but ignore a common multimodal scenario in the real world. Images and text can complement each other semantically, alleviating the semantic ambiguity suffered in text-only modality. Motivated by these, in this paper, we explore a problem of grounded multimodal procedural entity recognition (GMPER), aiming to detect the entity and the corresponding bounding box groundings in image (i.e., visual entities). A new dataset (Wiki-GMPER) is bult and extensive experiments are conducted to evaluate the effectiveness of our proposed model.
%U https://aclanthology.org/2024.lrec-main.702
%P 7971-7981
Markdown (Informal)
[Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline](https://aclanthology.org/2024.lrec-main.702) (Ren et al., LREC-COLING 2024)
ACL