@inproceedings{katyal-etal-2023-teampn,
title = "team{PN} at {S}em{E}val-2023 Task 1: Visual Word Sense Disambiguation Using Zero-Shot {M}ulti{M}odal Approach",
author = "Katyal, Nikita and
Rajpoot, Pawan and
Tamilarasu, Subhanandh and
Mustafi, Joy",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.63",
doi = "10.18653/v1/2023.semeval-1.63",
pages = "457--461",
abstract = "Visual Word Sense Disambiguation shared task at SemEval-2023 aims to identify an image corresponding to the intended meaning of a given ambiguous word (with related context) from a set of candidate images. The lack of textual description for the candidate image and the corresponding word{'}s ambiguity makes it a challenging problem. This paper describes teamPN{'}s multi-modal and modular approach to solving this in English track of the task. We efficiently used recent multi-modal pre-trained models backed by real-time multi-modal knowledge graphs to augment textual knowledge for the images and select the best matching image accordingly. We outperformed the baseline model by {\textasciitilde}5 points and proposed a unique approach that can further work as a framework for other modular and knowledge-backed solutions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katyal-etal-2023-teampn">
<titleInfo>
<title>teamPN at SemEval-2023 Task 1: Visual Word Sense Disambiguation Using Zero-Shot MultiModal Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Katyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Rajpoot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subhanandh</namePart>
<namePart type="family">Tamilarasu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="family">Mustafi</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 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</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 shared task at SemEval-2023 aims to identify an image corresponding to the intended meaning of a given ambiguous word (with related context) from a set of candidate images. The lack of textual description for the candidate image and the corresponding word’s ambiguity makes it a challenging problem. This paper describes teamPN’s multi-modal and modular approach to solving this in English track of the task. We efficiently used recent multi-modal pre-trained models backed by real-time multi-modal knowledge graphs to augment textual knowledge for the images and select the best matching image accordingly. We outperformed the baseline model by ~5 points and proposed a unique approach that can further work as a framework for other modular and knowledge-backed solutions.</abstract>
<identifier type="citekey">katyal-etal-2023-teampn</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.63</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.63</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>457</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T teamPN at SemEval-2023 Task 1: Visual Word Sense Disambiguation Using Zero-Shot MultiModal Approach
%A Katyal, Nikita
%A Rajpoot, Pawan
%A Tamilarasu, Subhanandh
%A Mustafi, Joy
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F katyal-etal-2023-teampn
%X Visual Word Sense Disambiguation shared task at SemEval-2023 aims to identify an image corresponding to the intended meaning of a given ambiguous word (with related context) from a set of candidate images. The lack of textual description for the candidate image and the corresponding word’s ambiguity makes it a challenging problem. This paper describes teamPN’s multi-modal and modular approach to solving this in English track of the task. We efficiently used recent multi-modal pre-trained models backed by real-time multi-modal knowledge graphs to augment textual knowledge for the images and select the best matching image accordingly. We outperformed the baseline model by ~5 points and proposed a unique approach that can further work as a framework for other modular and knowledge-backed solutions.
%R 10.18653/v1/2023.semeval-1.63
%U https://aclanthology.org/2023.semeval-1.63
%U https://doi.org/10.18653/v1/2023.semeval-1.63
%P 457-461
Markdown (Informal)
[teamPN at SemEval-2023 Task 1: Visual Word Sense Disambiguation Using Zero-Shot MultiModal Approach](https://aclanthology.org/2023.semeval-1.63) (Katyal et al., SemEval 2023)
ACL