@inproceedings{li-etal-2023-augmenters,
title = "Augmenters at {S}em{E}val-2023 Task 1: Enhancing {CLIP} in Handling Compositionality and Ambiguity for Zero-Shot Visual {WSD} through Prompt Augmentation and Text-To-Image Diffusion",
author = "Li, Jie and
Shiue, Yow-Ting and
Shih, Yong-Siang and
Geiping, Jonas",
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-1.5",
doi = "10.18653/v1/2023.semeval-1.5",
pages = "44--49",
abstract = "This paper describes our zero-shot approachesfor the Visual Word Sense Disambiguation(VWSD) Task in English. Our preliminarystudy shows that the simple approach of match-ing candidate images with the phrase usingCLIP suffers from the many-to-many natureof image-text pairs. We find that the CLIP textencoder may have limited abilities in captur-ing the compositionality in natural language. Conversely, the descriptive focus of the phrasevaries from instance to instance. We addressthese issues in our two systems, Augment-CLIPand Stable Diffusion Sampling (SD Sampling).Augment-CLIP augments the text prompt bygenerating sentences that contain the contextphrase with the help of large language mod-els (LLMs). We further explore CLIP modelsin other languages, as the an ambiguous wordmay be translated into an unambiguous one inthe other language. SD Sampling uses text-to-image Stable Diffusion to generate multipleimages from the given phrase, increasing thelikelihood that a subset of images match theone that paired with the text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-augmenters">
<titleInfo>
<title>Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yow-Ting</namePart>
<namePart type="family">Shiue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong-Siang</namePart>
<namePart type="family">Shih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Geiping</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 zero-shot approachesfor the Visual Word Sense Disambiguation(VWSD) Task in English. Our preliminarystudy shows that the simple approach of match-ing candidate images with the phrase usingCLIP suffers from the many-to-many natureof image-text pairs. We find that the CLIP textencoder may have limited abilities in captur-ing the compositionality in natural language. Conversely, the descriptive focus of the phrasevaries from instance to instance. We addressthese issues in our two systems, Augment-CLIPand Stable Diffusion Sampling (SD Sampling).Augment-CLIP augments the text prompt bygenerating sentences that contain the contextphrase with the help of large language mod-els (LLMs). We further explore CLIP modelsin other languages, as the an ambiguous wordmay be translated into an unambiguous one inthe other language. SD Sampling uses text-to-image Stable Diffusion to generate multipleimages from the given phrase, increasing thelikelihood that a subset of images match theone that paired with the text.</abstract>
<identifier type="citekey">li-etal-2023-augmenters</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.5</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>44</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion
%A Li, Jie
%A Shiue, Yow-Ting
%A Shih, Yong-Siang
%A Geiping, Jonas
%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-augmenters
%X This paper describes our zero-shot approachesfor the Visual Word Sense Disambiguation(VWSD) Task in English. Our preliminarystudy shows that the simple approach of match-ing candidate images with the phrase usingCLIP suffers from the many-to-many natureof image-text pairs. We find that the CLIP textencoder may have limited abilities in captur-ing the compositionality in natural language. Conversely, the descriptive focus of the phrasevaries from instance to instance. We addressthese issues in our two systems, Augment-CLIPand Stable Diffusion Sampling (SD Sampling).Augment-CLIP augments the text prompt bygenerating sentences that contain the contextphrase with the help of large language mod-els (LLMs). We further explore CLIP modelsin other languages, as the an ambiguous wordmay be translated into an unambiguous one inthe other language. SD Sampling uses text-to-image Stable Diffusion to generate multipleimages from the given phrase, increasing thelikelihood that a subset of images match theone that paired with the text.
%R 10.18653/v1/2023.semeval-1.5
%U https://aclanthology.org/2023.semeval-1.5
%U https://doi.org/10.18653/v1/2023.semeval-1.5
%P 44-49
Markdown (Informal)
[Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion](https://aclanthology.org/2023.semeval-1.5) (Li et al., SemEval 2023)
ACL