@inproceedings{zhang-etal-2023-incorporating-object,
title = "Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing",
author = "Zhang, Ying and
Fan, Wenbo and
Song, Kehui and
Zhao, Yu and
Sui, Xuhui and
Yuan, Xiaojie",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.1027",
doi = "10.18653/v1/2023.findings-emnlp.1027",
pages = "15380--15390",
abstract = "Fine-grained entity typing (FGET) aims to assign appropriate fine-grained types to entity mentions within their context, which is an important foundational task in natural language processing. Previous approaches for FGET only utilized textual context information. However, in the form of short text, the contextual semantic information is often insufficient for FGET. In many real-world scenarios, text is often accompanied by images, and the visual context is valuable for FGET. To this end, we firstly propose a new task called multimodal fine-grained entity typing (MFGET). Then we construct a large-scale dataset for multimodal fine-grained entity typing called MFIGER based on FIGER. To fully leverage both textual and visual information, we propose a novel Multimodal Object-Level Visual Context Network (MOVCNet). MOVCNet can capture fine-grained semantic information by detecting objects in images, and effectively merge both textual and visual context. Experimental results demonstrate that our approach achieves superior classification performance compared to previous text-based approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-incorporating-object">
<titleInfo>
<title>Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kehui</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuhui</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-grained entity typing (FGET) aims to assign appropriate fine-grained types to entity mentions within their context, which is an important foundational task in natural language processing. Previous approaches for FGET only utilized textual context information. However, in the form of short text, the contextual semantic information is often insufficient for FGET. In many real-world scenarios, text is often accompanied by images, and the visual context is valuable for FGET. To this end, we firstly propose a new task called multimodal fine-grained entity typing (MFGET). Then we construct a large-scale dataset for multimodal fine-grained entity typing called MFIGER based on FIGER. To fully leverage both textual and visual information, we propose a novel Multimodal Object-Level Visual Context Network (MOVCNet). MOVCNet can capture fine-grained semantic information by detecting objects in images, and effectively merge both textual and visual context. Experimental results demonstrate that our approach achieves superior classification performance compared to previous text-based approaches.</abstract>
<identifier type="citekey">zhang-etal-2023-incorporating-object</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.1027</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.1027</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15380</start>
<end>15390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing
%A Zhang, Ying
%A Fan, Wenbo
%A Song, Kehui
%A Zhao, Yu
%A Sui, Xuhui
%A Yuan, Xiaojie
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-incorporating-object
%X Fine-grained entity typing (FGET) aims to assign appropriate fine-grained types to entity mentions within their context, which is an important foundational task in natural language processing. Previous approaches for FGET only utilized textual context information. However, in the form of short text, the contextual semantic information is often insufficient for FGET. In many real-world scenarios, text is often accompanied by images, and the visual context is valuable for FGET. To this end, we firstly propose a new task called multimodal fine-grained entity typing (MFGET). Then we construct a large-scale dataset for multimodal fine-grained entity typing called MFIGER based on FIGER. To fully leverage both textual and visual information, we propose a novel Multimodal Object-Level Visual Context Network (MOVCNet). MOVCNet can capture fine-grained semantic information by detecting objects in images, and effectively merge both textual and visual context. Experimental results demonstrate that our approach achieves superior classification performance compared to previous text-based approaches.
%R 10.18653/v1/2023.findings-emnlp.1027
%U https://aclanthology.org/2023.findings-emnlp.1027
%U https://doi.org/10.18653/v1/2023.findings-emnlp.1027
%P 15380-15390
Markdown (Informal)
[Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing](https://aclanthology.org/2023.findings-emnlp.1027) (Zhang et al., Findings 2023)
ACL