@inproceedings{vaiani-etal-2023-polito,
title = "{P}oli{T}o at {S}em{E}val-2023 Task 1: {CLIP}-based Visual-Word Sense Disambiguation Based on Back-Translation",
author = "Vaiani, Lorenzo and
Cagliero, Luca and
Garza, Paolo",
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-1.199",
doi = "10.18653/v1/2023.semeval-1.199",
pages = "1447--1453",
abstract = "Visual-Word Sense Disambiguation (V-WSD) entails resolving the linguistic ambiguity in a text by selecting a clarifying image from a set of (potentially misleading) candidates. In this paper, we address V-WSD using a state-of-the-art Image-Text Retrieval system, namely CLIP. We propose to alleviate the linguistic ambiguity across multiple domains and languages via text and image augmentation. To augment the textual content we rely on back-translation with the aid of a variety of auxiliary languages. The approach based on finetuning CLIP on the full phrases is effective in accurately disambiguating words and incorporating back-translation enhance the system{'}s robustness and performance on the test samples written in Indo-European languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaiani-etal-2023-polito">
<titleInfo>
<title>PoliTo at SemEval-2023 Task 1: CLIP-based Visual-Word Sense Disambiguation Based on Back-Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Vaiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Cagliero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Garza</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 (V-WSD) entails resolving the linguistic ambiguity in a text by selecting a clarifying image from a set of (potentially misleading) candidates. In this paper, we address V-WSD using a state-of-the-art Image-Text Retrieval system, namely CLIP. We propose to alleviate the linguistic ambiguity across multiple domains and languages via text and image augmentation. To augment the textual content we rely on back-translation with the aid of a variety of auxiliary languages. The approach based on finetuning CLIP on the full phrases is effective in accurately disambiguating words and incorporating back-translation enhance the system’s robustness and performance on the test samples written in Indo-European languages.</abstract>
<identifier type="citekey">vaiani-etal-2023-polito</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.199</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.199</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1447</start>
<end>1453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoliTo at SemEval-2023 Task 1: CLIP-based Visual-Word Sense Disambiguation Based on Back-Translation
%A Vaiani, Lorenzo
%A Cagliero, Luca
%A Garza, Paolo
%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 vaiani-etal-2023-polito
%X Visual-Word Sense Disambiguation (V-WSD) entails resolving the linguistic ambiguity in a text by selecting a clarifying image from a set of (potentially misleading) candidates. In this paper, we address V-WSD using a state-of-the-art Image-Text Retrieval system, namely CLIP. We propose to alleviate the linguistic ambiguity across multiple domains and languages via text and image augmentation. To augment the textual content we rely on back-translation with the aid of a variety of auxiliary languages. The approach based on finetuning CLIP on the full phrases is effective in accurately disambiguating words and incorporating back-translation enhance the system’s robustness and performance on the test samples written in Indo-European languages.
%R 10.18653/v1/2023.semeval-1.199
%U https://aclanthology.org/2023.semeval-1.199
%U https://doi.org/10.18653/v1/2023.semeval-1.199
%P 1447-1453
Markdown (Informal)
[PoliTo at SemEval-2023 Task 1: CLIP-based Visual-Word Sense Disambiguation Based on Back-Translation](https://aclanthology.org/2023.semeval-1.199) (Vaiani et al., SemEval 2023)
ACL