@inproceedings{kwon-etal-2023-vision,
title = "Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information",
author = "Kwon, Sunjae and
Garodia, Rishabh and
Lee, Minhwa and
Yang, Zhichao and
Yu, Hong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.88",
doi = "10.18653/v1/2023.acl-long.88",
pages = "1583--1598",
abstract = "Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context. Previously, image-text matching models often suffered from recognizing polysemous words. This paper introduces an unsupervised VWSD approach that uses gloss information of an external lexical knowledge-base, especially the sense definitions. Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided. In addition, to ameliorate the out-of-dictionary (OOD) issue, we propose a context-aware definition generation with GPT-3. Experimental results show that the VWSD performance significantly increased with our Bayesian inference-based approach. In addition, our context-aware definition generation achieved prominent performance improvement in OOD examples exhibiting better performance than the existing definition generation method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kwon-etal-2023-vision">
<titleInfo>
<title>Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunjae</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Garodia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhichao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context. Previously, image-text matching models often suffered from recognizing polysemous words. This paper introduces an unsupervised VWSD approach that uses gloss information of an external lexical knowledge-base, especially the sense definitions. Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided. In addition, to ameliorate the out-of-dictionary (OOD) issue, we propose a context-aware definition generation with GPT-3. Experimental results show that the VWSD performance significantly increased with our Bayesian inference-based approach. In addition, our context-aware definition generation achieved prominent performance improvement in OOD examples exhibiting better performance than the existing definition generation method.</abstract>
<identifier type="citekey">kwon-etal-2023-vision</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.88</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.88</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1583</start>
<end>1598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information
%A Kwon, Sunjae
%A Garodia, Rishabh
%A Lee, Minhwa
%A Yang, Zhichao
%A Yu, Hong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kwon-etal-2023-vision
%X Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context. Previously, image-text matching models often suffered from recognizing polysemous words. This paper introduces an unsupervised VWSD approach that uses gloss information of an external lexical knowledge-base, especially the sense definitions. Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided. In addition, to ameliorate the out-of-dictionary (OOD) issue, we propose a context-aware definition generation with GPT-3. Experimental results show that the VWSD performance significantly increased with our Bayesian inference-based approach. In addition, our context-aware definition generation achieved prominent performance improvement in OOD examples exhibiting better performance than the existing definition generation method.
%R 10.18653/v1/2023.acl-long.88
%U https://aclanthology.org/2023.acl-long.88
%U https://doi.org/10.18653/v1/2023.acl-long.88
%P 1583-1598
Markdown (Informal)
[Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information](https://aclanthology.org/2023.acl-long.88) (Kwon et al., ACL 2023)
ACL