@inproceedings{zhang-etal-2023-gpl,
title = "{GPL} at {S}em{E}val-2023 Task 1: {W}ord{N}et and {CLIP} to Disambiguate Images",
author = "Zhang, Shibingfeng and
Nath, Shantanu and
Mazzaccara, Davide",
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-1.219",
doi = "10.18653/v1/2023.semeval-1.219",
pages = "1592--1597",
abstract = "Given a word in context, the task of VisualWord Sense Disambiguation consists of select-ing the correct image among a set of candidates. To select the correct image, we propose a so-lution blending text augmentation and multi-modal models. Text augmentation leverages thefine-grained semantic annotation from Word-Net to get a better representation of the tex-tual component. We then compare this sense-augmented text to the set of image using pre-trained multimodal models CLIP and ViLT. Oursystem has been ranked 16th for the Englishlanguage, achieving 68.5 points for hit rate and79.2 for mean reciprocal rank.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-gpl">
<titleInfo>
<title>GPL at SemEval-2023 Task 1: WordNet and CLIP to Disambiguate Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shibingfeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantanu</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Mazzaccara</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>Given a word in context, the task of VisualWord Sense Disambiguation consists of select-ing the correct image among a set of candidates. To select the correct image, we propose a so-lution blending text augmentation and multi-modal models. Text augmentation leverages thefine-grained semantic annotation from Word-Net to get a better representation of the tex-tual component. We then compare this sense-augmented text to the set of image using pre-trained multimodal models CLIP and ViLT. Oursystem has been ranked 16th for the Englishlanguage, achieving 68.5 points for hit rate and79.2 for mean reciprocal rank.</abstract>
<identifier type="citekey">zhang-etal-2023-gpl</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.219</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.219</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1592</start>
<end>1597</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPL at SemEval-2023 Task 1: WordNet and CLIP to Disambiguate Images
%A Zhang, Shibingfeng
%A Nath, Shantanu
%A Mazzaccara, Davide
%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 zhang-etal-2023-gpl
%X Given a word in context, the task of VisualWord Sense Disambiguation consists of select-ing the correct image among a set of candidates. To select the correct image, we propose a so-lution blending text augmentation and multi-modal models. Text augmentation leverages thefine-grained semantic annotation from Word-Net to get a better representation of the tex-tual component. We then compare this sense-augmented text to the set of image using pre-trained multimodal models CLIP and ViLT. Oursystem has been ranked 16th for the Englishlanguage, achieving 68.5 points for hit rate and79.2 for mean reciprocal rank.
%R 10.18653/v1/2023.semeval-1.219
%U https://aclanthology.org/2023.semeval-1.219
%U https://doi.org/10.18653/v1/2023.semeval-1.219
%P 1592-1597
Markdown (Informal)
[GPL at SemEval-2023 Task 1: WordNet and CLIP to Disambiguate Images](https://aclanthology.org/2023.semeval-1.219) (Zhang et al., SemEval 2023)
ACL