@inproceedings{yang-etal-2023-tam,
title = "{TAM} of {SCNU} at {S}em{E}val-2023 Task 1: {FCLL}: A Fine-grained Contrastive Language-Image Learning Model for Cross-language Visual Word Sense Disambiguation",
author = "Yang, Qihao and
Li, Yong and
Wang, Xuelin and
Li, Shunhao and
Hao, Tianyong",
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-1.70",
doi = "10.18653/v1/2023.semeval-1.70",
pages = "506--511",
abstract = "Visual Word Sense Disambiguation (WSD), as a fine-grained image-text retrieval task, aims to identify the images that are relevant to ambiguous target words or phrases. However, the difficulties of limited contextual information and cross-linguistic background knowledge in text processing make this task challenging. To alleviate this issue, we propose a Fine-grained Contrastive Language-Image Learning (FCLL) model, which learns fine-grained image-text knowledge by employing a new fine-grained contrastive learning mechanism and enriches contextual information by establishing relationship between concepts and sentences. In addition, a new multimodal-multilingual knowledge base involving ambiguous target words is constructed for visual WSD. Experiment results on the benchmark datasets from SemEval-2023 Task 1 show that our FCLL ranks at the first in overall evaluation with an average H@1 of 72.56{\textbackslash}{\%} and an average MRR of 82.22{\textbackslash}{\%}. The results demonstrate that FCLL is effective in inference on fine-grained language-vision knowledge. Source codes and the knowledge base are publicly available at \url{https://github.com/CharlesYang030/FCLL}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2023-tam">
<titleInfo>
<title>TAM of SCNU at SemEval-2023 Task 1: FCLL: A Fine-grained Contrastive Language-Image Learning Model for Cross-language Visual Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qihao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuelin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shunhao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyong</namePart>
<namePart type="family">Hao</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 (WSD), as a fine-grained image-text retrieval task, aims to identify the images that are relevant to ambiguous target words or phrases. However, the difficulties of limited contextual information and cross-linguistic background knowledge in text processing make this task challenging. To alleviate this issue, we propose a Fine-grained Contrastive Language-Image Learning (FCLL) model, which learns fine-grained image-text knowledge by employing a new fine-grained contrastive learning mechanism and enriches contextual information by establishing relationship between concepts and sentences. In addition, a new multimodal-multilingual knowledge base involving ambiguous target words is constructed for visual WSD. Experiment results on the benchmark datasets from SemEval-2023 Task 1 show that our FCLL ranks at the first in overall evaluation with an average H@1 of 72.56\textbackslash% and an average MRR of 82.22\textbackslash%. The results demonstrate that FCLL is effective in inference on fine-grained language-vision knowledge. Source codes and the knowledge base are publicly available at https://github.com/CharlesYang030/FCLL.</abstract>
<identifier type="citekey">yang-etal-2023-tam</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.70</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.70</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>506</start>
<end>511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TAM of SCNU at SemEval-2023 Task 1: FCLL: A Fine-grained Contrastive Language-Image Learning Model for Cross-language Visual Word Sense Disambiguation
%A Yang, Qihao
%A Li, Yong
%A Wang, Xuelin
%A Li, Shunhao
%A Hao, Tianyong
%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 yang-etal-2023-tam
%X Visual Word Sense Disambiguation (WSD), as a fine-grained image-text retrieval task, aims to identify the images that are relevant to ambiguous target words or phrases. However, the difficulties of limited contextual information and cross-linguistic background knowledge in text processing make this task challenging. To alleviate this issue, we propose a Fine-grained Contrastive Language-Image Learning (FCLL) model, which learns fine-grained image-text knowledge by employing a new fine-grained contrastive learning mechanism and enriches contextual information by establishing relationship between concepts and sentences. In addition, a new multimodal-multilingual knowledge base involving ambiguous target words is constructed for visual WSD. Experiment results on the benchmark datasets from SemEval-2023 Task 1 show that our FCLL ranks at the first in overall evaluation with an average H@1 of 72.56\textbackslash% and an average MRR of 82.22\textbackslash%. The results demonstrate that FCLL is effective in inference on fine-grained language-vision knowledge. Source codes and the knowledge base are publicly available at https://github.com/CharlesYang030/FCLL.
%R 10.18653/v1/2023.semeval-1.70
%U https://aclanthology.org/2023.semeval-1.70
%U https://doi.org/10.18653/v1/2023.semeval-1.70
%P 506-511
Markdown (Informal)
[TAM of SCNU at SemEval-2023 Task 1: FCLL: A Fine-grained Contrastive Language-Image Learning Model for Cross-language Visual Word Sense Disambiguation](https://aclanthology.org/2023.semeval-1.70) (Yang et al., SemEval 2023)
ACL