@inproceedings{molavi-zeinali-2023-slt,
title = "{SLT} at {S}em{E}val-2023 Task 1: Enhancing Visual Word Sense Disambiguation through Image Text Retrieval using {BLIP}",
author = "Molavi, Mohammadreza and
Zeinali, Hossein",
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-1.264",
doi = "10.18653/v1/2023.semeval-1.264",
pages = "1921--1925",
abstract = "Based on recent progress in image-text retrieval techniques, this paper presents a fine-tuned model for the Visual Word Sense Disambiguation (VWSD) task. The proposed system fine-tunes a pre-trained model using ITC and ITM losses and employs a candidate selection approach for faster inference. The system was trained on the VWSD task dataset and evaluated on a separate test set using Mean Reciprocal Rank (MRR) metric. Additionally, the system was tested on the provided test set which contained Persian and Italian languages, and the results were evaluated on each language separately. Our proposed system demonstrates the potential of fine-tuning pre-trained models for complex language tasks and provides insights for further research in the field of image text retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="molavi-zeinali-2023-slt">
<titleInfo>
<title>SLT at SemEval-2023 Task 1: Enhancing Visual Word Sense Disambiguation through Image Text Retrieval using BLIP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammadreza</namePart>
<namePart type="family">Molavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Zeinali</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>Based on recent progress in image-text retrieval techniques, this paper presents a fine-tuned model for the Visual Word Sense Disambiguation (VWSD) task. The proposed system fine-tunes a pre-trained model using ITC and ITM losses and employs a candidate selection approach for faster inference. The system was trained on the VWSD task dataset and evaluated on a separate test set using Mean Reciprocal Rank (MRR) metric. Additionally, the system was tested on the provided test set which contained Persian and Italian languages, and the results were evaluated on each language separately. Our proposed system demonstrates the potential of fine-tuning pre-trained models for complex language tasks and provides insights for further research in the field of image text retrieval.</abstract>
<identifier type="citekey">molavi-zeinali-2023-slt</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.264</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.264</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1921</start>
<end>1925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLT at SemEval-2023 Task 1: Enhancing Visual Word Sense Disambiguation through Image Text Retrieval using BLIP
%A Molavi, Mohammadreza
%A Zeinali, Hossein
%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 molavi-zeinali-2023-slt
%X Based on recent progress in image-text retrieval techniques, this paper presents a fine-tuned model for the Visual Word Sense Disambiguation (VWSD) task. The proposed system fine-tunes a pre-trained model using ITC and ITM losses and employs a candidate selection approach for faster inference. The system was trained on the VWSD task dataset and evaluated on a separate test set using Mean Reciprocal Rank (MRR) metric. Additionally, the system was tested on the provided test set which contained Persian and Italian languages, and the results were evaluated on each language separately. Our proposed system demonstrates the potential of fine-tuning pre-trained models for complex language tasks and provides insights for further research in the field of image text retrieval.
%R 10.18653/v1/2023.semeval-1.264
%U https://aclanthology.org/2023.semeval-1.264
%U https://doi.org/10.18653/v1/2023.semeval-1.264
%P 1921-1925
Markdown (Informal)
[SLT at SemEval-2023 Task 1: Enhancing Visual Word Sense Disambiguation through Image Text Retrieval using BLIP](https://aclanthology.org/2023.semeval-1.264) (Molavi & Zeinali, SemEval 2023)
ACL