@inproceedings{mijatovic-etal-2023-rcln,
title = "{RCLN} at {S}em{E}val-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual {WSD}",
author = "Mijatovic, Antonina and
Buscaldi, Davide and
Borisova, Ekaterina",
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-1.301",
doi = "10.18653/v1/2023.semeval-1.301",
pages = "2174--2178",
abstract = "This paper describes the participation of the RCLN team at the Visual Word Sense Disambiguation task at SemEval 2023. The participation was focused on the use of CLIP as a base model for the matching between text and images with additional information coming from captions generated from images and the generation of images from the prompt text using Stable Diffusion. The results we obtained are not particularly good, but interestingly enough, we were able to improve over the CLIP baseline in Italian by recurring simply to the generated images.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mijatovic-etal-2023-rcln">
<titleInfo>
<title>RCLN at SemEval-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual WSD</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonina</namePart>
<namePart type="family">Mijatovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Buscaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Borisova</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>This paper describes the participation of the RCLN team at the Visual Word Sense Disambiguation task at SemEval 2023. The participation was focused on the use of CLIP as a base model for the matching between text and images with additional information coming from captions generated from images and the generation of images from the prompt text using Stable Diffusion. The results we obtained are not particularly good, but interestingly enough, we were able to improve over the CLIP baseline in Italian by recurring simply to the generated images.</abstract>
<identifier type="citekey">mijatovic-etal-2023-rcln</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.301</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.301</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2174</start>
<end>2178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RCLN at SemEval-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual WSD
%A Mijatovic, Antonina
%A Buscaldi, Davide
%A Borisova, Ekaterina
%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 mijatovic-etal-2023-rcln
%X This paper describes the participation of the RCLN team at the Visual Word Sense Disambiguation task at SemEval 2023. The participation was focused on the use of CLIP as a base model for the matching between text and images with additional information coming from captions generated from images and the generation of images from the prompt text using Stable Diffusion. The results we obtained are not particularly good, but interestingly enough, we were able to improve over the CLIP baseline in Italian by recurring simply to the generated images.
%R 10.18653/v1/2023.semeval-1.301
%U https://aclanthology.org/2023.semeval-1.301
%U https://doi.org/10.18653/v1/2023.semeval-1.301
%P 2174-2178
Markdown (Informal)
[RCLN at SemEval-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual WSD](https://aclanthology.org/2023.semeval-1.301) (Mijatovic et al., SemEval 2023)
ACL