@inproceedings{pirhadi-etal-2023-pmcoders,
title = "{PMC}oders at {S}em{E}val-2023 Task 1: {RA}lt{CLIP}: Use Relative {A}lt{CLIP} Features to Rank",
author = "Pirhadi, Mohammad Javad and
Mirzaei, Motahhare and
Mohammadi, Mohammad Reza and
Eetemadi, Sauleh",
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-1.242",
doi = "10.18653/v1/2023.semeval-1.242",
pages = "1751--1755",
abstract = "Visual Word Sense Disambiguation (VWSD) task aims to find the most related image among 10 images to an ambiguous word in some limited textual context. In this work, we use AltCLIP features and a 3-layer standard transformer encoder to compare the cosine similarity between the given phrase and different images. Also, we improve our model{'}s generalization by using a subset of LAION-5B. The best official baseline achieves 37.20{\%} and 54.39{\%} macro-averaged hit rate and MRR (Mean Reciprocal Rank) respectively. Our best configuration reaches 39.61{\%} and 56.78{\%} macro-averaged hit rate and MRR respectively. The code will be made publicly available on GitHub.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pirhadi-etal-2023-pmcoders">
<titleInfo>
<title>PMCoders at SemEval-2023 Task 1: RAltCLIP: Use Relative AltCLIP Features to Rank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Javad</namePart>
<namePart type="family">Pirhadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Motahhare</namePart>
<namePart type="family">Mirzaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Reza</namePart>
<namePart type="family">Mohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sauleh</namePart>
<namePart type="family">Eetemadi</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 (VWSD) task aims to find the most related image among 10 images to an ambiguous word in some limited textual context. In this work, we use AltCLIP features and a 3-layer standard transformer encoder to compare the cosine similarity between the given phrase and different images. Also, we improve our model’s generalization by using a subset of LAION-5B. The best official baseline achieves 37.20% and 54.39% macro-averaged hit rate and MRR (Mean Reciprocal Rank) respectively. Our best configuration reaches 39.61% and 56.78% macro-averaged hit rate and MRR respectively. The code will be made publicly available on GitHub.</abstract>
<identifier type="citekey">pirhadi-etal-2023-pmcoders</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.242</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.242</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1751</start>
<end>1755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PMCoders at SemEval-2023 Task 1: RAltCLIP: Use Relative AltCLIP Features to Rank
%A Pirhadi, Mohammad Javad
%A Mirzaei, Motahhare
%A Mohammadi, Mohammad Reza
%A Eetemadi, Sauleh
%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 pirhadi-etal-2023-pmcoders
%X Visual Word Sense Disambiguation (VWSD) task aims to find the most related image among 10 images to an ambiguous word in some limited textual context. In this work, we use AltCLIP features and a 3-layer standard transformer encoder to compare the cosine similarity between the given phrase and different images. Also, we improve our model’s generalization by using a subset of LAION-5B. The best official baseline achieves 37.20% and 54.39% macro-averaged hit rate and MRR (Mean Reciprocal Rank) respectively. Our best configuration reaches 39.61% and 56.78% macro-averaged hit rate and MRR respectively. The code will be made publicly available on GitHub.
%R 10.18653/v1/2023.semeval-1.242
%U https://aclanthology.org/2023.semeval-1.242
%U https://doi.org/10.18653/v1/2023.semeval-1.242
%P 1751-1755
Markdown (Informal)
[PMCoders at SemEval-2023 Task 1: RAltCLIP: Use Relative AltCLIP Features to Rank](https://aclanthology.org/2023.semeval-1.242) (Pirhadi et al., SemEval 2023)
ACL