@inproceedings{diem-etal-2023-university,
title = "{U}niversity of {H}ildesheim at {S}em{E}val-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation",
author = "Diem, Sebastian and
Im, Chan Jong and
Mandl, Thomas",
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-1.18",
doi = "10.18653/v1/2023.semeval-1.18",
pages = "130--135",
abstract = "Multimodal ambiguity is a challenge for understanding text and images. Large pre-trained models have reached a high level of quality already. This paper presents an implementation for solving a image disambiguation task relying solely on the knowledge captured in multimodal and language models. Within the task 1 of SemEval 2023 (Visual Word Sense Disambiguation), this approach managed to achieve an MRR of 0.738 using CLIP-Large and the OPT model for generating text. Applying a generative model to create more text given a phrase with an ambiguous word leads to an improvement of our results. The performance gain from a bigger language model is larger than the performance gain from using the lager CLIP model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diem-etal-2023-university">
<titleInfo>
<title>University of Hildesheim at SemEval-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Diem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Jong</namePart>
<namePart type="family">Im</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Mandl</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>Multimodal ambiguity is a challenge for understanding text and images. Large pre-trained models have reached a high level of quality already. This paper presents an implementation for solving a image disambiguation task relying solely on the knowledge captured in multimodal and language models. Within the task 1 of SemEval 2023 (Visual Word Sense Disambiguation), this approach managed to achieve an MRR of 0.738 using CLIP-Large and the OPT model for generating text. Applying a generative model to create more text given a phrase with an ambiguous word leads to an improvement of our results. The performance gain from a bigger language model is larger than the performance gain from using the lager CLIP model.</abstract>
<identifier type="citekey">diem-etal-2023-university</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.18</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.18</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>130</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T University of Hildesheim at SemEval-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation
%A Diem, Sebastian
%A Im, Chan Jong
%A Mandl, Thomas
%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 diem-etal-2023-university
%X Multimodal ambiguity is a challenge for understanding text and images. Large pre-trained models have reached a high level of quality already. This paper presents an implementation for solving a image disambiguation task relying solely on the knowledge captured in multimodal and language models. Within the task 1 of SemEval 2023 (Visual Word Sense Disambiguation), this approach managed to achieve an MRR of 0.738 using CLIP-Large and the OPT model for generating text. Applying a generative model to create more text given a phrase with an ambiguous word leads to an improvement of our results. The performance gain from a bigger language model is larger than the performance gain from using the lager CLIP model.
%R 10.18653/v1/2023.semeval-1.18
%U https://aclanthology.org/2023.semeval-1.18
%U https://doi.org/10.18653/v1/2023.semeval-1.18
%P 130-135
Markdown (Informal)
[University of Hildesheim at SemEval-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation](https://aclanthology.org/2023.semeval-1.18) (Diem et al., SemEval 2023)
ACL