@inproceedings{zhang-etal-2023-ck,
title = "{CK}-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension",
author = "Zhang, Zhi and
Yannakoudakis, Helen and
Zhen, Xiantong and
Shutova, Ekaterina",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.196",
doi = "10.18653/v1/2023.findings-eacl.196",
pages = "2586--2596",
abstract = "The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity. In this paper, we specifically focus on referring expression comprehension with commonsense knowledge (KB-Ref), a task which typically requires reasoning beyond spatial, visual or semantic information. We propose a novel framework for Commonsense Knowledge Enhanced Transformers (CK-Transformer) which effectively integrates commonsense knowledge into the representations of objects in an image, facilitating identification of the target objects referred to by the expressions. We conduct extensive experiments on several benchmarks for the task of KB-Ref. Our results show that the proposed CK-Transformer achieves a new state of the art, with an absolute improvement of 3.14{\%} accuracy over the existing state of the art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-ck">
<titleInfo>
<title>CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiantong</namePart>
<namePart type="family">Zhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity. In this paper, we specifically focus on referring expression comprehension with commonsense knowledge (KB-Ref), a task which typically requires reasoning beyond spatial, visual or semantic information. We propose a novel framework for Commonsense Knowledge Enhanced Transformers (CK-Transformer) which effectively integrates commonsense knowledge into the representations of objects in an image, facilitating identification of the target objects referred to by the expressions. We conduct extensive experiments on several benchmarks for the task of KB-Ref. Our results show that the proposed CK-Transformer achieves a new state of the art, with an absolute improvement of 3.14% accuracy over the existing state of the art.</abstract>
<identifier type="citekey">zhang-etal-2023-ck</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.196</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.196</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>2586</start>
<end>2596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension
%A Zhang, Zhi
%A Yannakoudakis, Helen
%A Zhen, Xiantong
%A Shutova, Ekaterina
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F zhang-etal-2023-ck
%X The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity. In this paper, we specifically focus on referring expression comprehension with commonsense knowledge (KB-Ref), a task which typically requires reasoning beyond spatial, visual or semantic information. We propose a novel framework for Commonsense Knowledge Enhanced Transformers (CK-Transformer) which effectively integrates commonsense knowledge into the representations of objects in an image, facilitating identification of the target objects referred to by the expressions. We conduct extensive experiments on several benchmarks for the task of KB-Ref. Our results show that the proposed CK-Transformer achieves a new state of the art, with an absolute improvement of 3.14% accuracy over the existing state of the art.
%R 10.18653/v1/2023.findings-eacl.196
%U https://aclanthology.org/2023.findings-eacl.196
%U https://doi.org/10.18653/v1/2023.findings-eacl.196
%P 2586-2596
Markdown (Informal)
[CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension](https://aclanthology.org/2023.findings-eacl.196) (Zhang et al., Findings 2023)
ACL