@inproceedings{zhao-etal-2022-entity,
title = "Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition",
author = "Zhao, Gang and
Dong, Guanting and
Shi, Yidong and
Yan, Haolong and
Xu, Weiran and
Li, Si",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.473",
doi = "10.18653/v1/2022.findings-emnlp.473",
pages = "6345--6350",
abstract = "Multimodal Named Entity Recognition (MNER) faces two specific challenges: 1) How to capture useful entity-related visual information. 2) How to alleviate the interference of visual noise. Previous works have gained progress by improving interacting mechanisms or seeking for better visual features. However, existing methods neglect the integrity of entity semantics and conduct cross-modal interaction at token-level, which cuts apart the semantics of entities and makes non-entity tokens easily interfered with by irrelevant visual noise. Thus in this paper, we propose an end-to-end heterogeneous Graph-based Entity-level Interacting model (GEI) for MNER. GEI first utilizes a span detection subtask to obtain entity representations, which serve as the bridge between two modalities. Then, the heterogeneous graph interacting network interacts entity with object nodes to capture entity-related visual information, and fuses it into only entity-associated tokens to rid non-entity tokens of the visual noise. Experiments on two widely used datasets demonstrate the effectiveness of our method. Our code will be available at https://github.com/GangZhao98/GEI.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2022-entity">
<titleInfo>
<title>Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanting</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yidong</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haolong</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiran</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Named Entity Recognition (MNER) faces two specific challenges: 1) How to capture useful entity-related visual information. 2) How to alleviate the interference of visual noise. Previous works have gained progress by improving interacting mechanisms or seeking for better visual features. However, existing methods neglect the integrity of entity semantics and conduct cross-modal interaction at token-level, which cuts apart the semantics of entities and makes non-entity tokens easily interfered with by irrelevant visual noise. Thus in this paper, we propose an end-to-end heterogeneous Graph-based Entity-level Interacting model (GEI) for MNER. GEI first utilizes a span detection subtask to obtain entity representations, which serve as the bridge between two modalities. Then, the heterogeneous graph interacting network interacts entity with object nodes to capture entity-related visual information, and fuses it into only entity-associated tokens to rid non-entity tokens of the visual noise. Experiments on two widely used datasets demonstrate the effectiveness of our method. Our code will be available at https://github.com/GangZhao98/GEI.</abstract>
<identifier type="citekey">zhao-etal-2022-entity</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.473</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.473</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6345</start>
<end>6350</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition
%A Zhao, Gang
%A Dong, Guanting
%A Shi, Yidong
%A Yan, Haolong
%A Xu, Weiran
%A Li, Si
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhao-etal-2022-entity
%X Multimodal Named Entity Recognition (MNER) faces two specific challenges: 1) How to capture useful entity-related visual information. 2) How to alleviate the interference of visual noise. Previous works have gained progress by improving interacting mechanisms or seeking for better visual features. However, existing methods neglect the integrity of entity semantics and conduct cross-modal interaction at token-level, which cuts apart the semantics of entities and makes non-entity tokens easily interfered with by irrelevant visual noise. Thus in this paper, we propose an end-to-end heterogeneous Graph-based Entity-level Interacting model (GEI) for MNER. GEI first utilizes a span detection subtask to obtain entity representations, which serve as the bridge between two modalities. Then, the heterogeneous graph interacting network interacts entity with object nodes to capture entity-related visual information, and fuses it into only entity-associated tokens to rid non-entity tokens of the visual noise. Experiments on two widely used datasets demonstrate the effectiveness of our method. Our code will be available at https://github.com/GangZhao98/GEI.
%R 10.18653/v1/2022.findings-emnlp.473
%U https://aclanthology.org/2022.findings-emnlp.473
%U https://doi.org/10.18653/v1/2022.findings-emnlp.473
%P 6345-6350
Markdown (Informal)
[Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition](https://aclanthology.org/2022.findings-emnlp.473) (Zhao et al., Findings 2022)
ACL