@inproceedings{li-etal-2023-rutgers,
title = "Rutgers Multimedia Image Processing Lab at {S}em{E}val-2023 Task-1: Text-Augmentation-based Approach for Visual Word Sense Disambiguation",
author = "Li, Keyi and
Yang, Sen and
Gao, Chenyang and
Marsic, Ivan",
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-1.204",
doi = "10.18653/v1/2023.semeval-1.204",
pages = "1483--1490",
abstract = "This paper describes our system used in SemEval-2023 Task-1: Visual Word Sense Disambiguation (VWSD). The VWSD task is to identify the correct image that corresponds to an ambiguous target word given limited textual context. To reduce word ambiguity and enhance image selection, we proposed several text augmentation techniques, such as prompting, WordNet synonyms, and text generation. We experimented with different vision-language pre-trained models to capture the joint features of the augmented text and image. Our approach achieved the best performance using a combination of GPT-3 text generation and the CLIP model. On the multilingual test sets, our system achieved an average hit rate (at top-1) of 51.11 and a mean reciprocal rank of 65.69.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-rutgers">
<titleInfo>
<title>Rutgers Multimedia Image Processing Lab at SemEval-2023 Task-1: Text-Augmentation-based Approach for Visual Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Marsic</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 our system used in SemEval-2023 Task-1: Visual Word Sense Disambiguation (VWSD). The VWSD task is to identify the correct image that corresponds to an ambiguous target word given limited textual context. To reduce word ambiguity and enhance image selection, we proposed several text augmentation techniques, such as prompting, WordNet synonyms, and text generation. We experimented with different vision-language pre-trained models to capture the joint features of the augmented text and image. Our approach achieved the best performance using a combination of GPT-3 text generation and the CLIP model. On the multilingual test sets, our system achieved an average hit rate (at top-1) of 51.11 and a mean reciprocal rank of 65.69.</abstract>
<identifier type="citekey">li-etal-2023-rutgers</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.204</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.204</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1483</start>
<end>1490</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rutgers Multimedia Image Processing Lab at SemEval-2023 Task-1: Text-Augmentation-based Approach for Visual Word Sense Disambiguation
%A Li, Keyi
%A Yang, Sen
%A Gao, Chenyang
%A Marsic, Ivan
%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 li-etal-2023-rutgers
%X This paper describes our system used in SemEval-2023 Task-1: Visual Word Sense Disambiguation (VWSD). The VWSD task is to identify the correct image that corresponds to an ambiguous target word given limited textual context. To reduce word ambiguity and enhance image selection, we proposed several text augmentation techniques, such as prompting, WordNet synonyms, and text generation. We experimented with different vision-language pre-trained models to capture the joint features of the augmented text and image. Our approach achieved the best performance using a combination of GPT-3 text generation and the CLIP model. On the multilingual test sets, our system achieved an average hit rate (at top-1) of 51.11 and a mean reciprocal rank of 65.69.
%R 10.18653/v1/2023.semeval-1.204
%U https://aclanthology.org/2023.semeval-1.204
%U https://doi.org/10.18653/v1/2023.semeval-1.204
%P 1483-1490
Markdown (Informal)
[Rutgers Multimedia Image Processing Lab at SemEval-2023 Task-1: Text-Augmentation-based Approach for Visual Word Sense Disambiguation](https://aclanthology.org/2023.semeval-1.204) (Li et al., SemEval 2023)
ACL