@inproceedings{messina-etal-2021-aimh,
title = "{AIMH} at {S}em{E}val-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models",
author = "Messina, Nicola and
Falchi, Fabrizio and
Gennaro, Claudio and
Amato, Giuseppe",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.140",
doi = "10.18653/v1/2021.semeval-1.140",
pages = "1020--1026",
abstract = "This paper describes the system used by the AIMH Team to approach the SemEval Task 6. We propose an approach that relies on an architecture based on the transformer model to process multimodal content (text and images) in memes. Our architecture, called DVTT (Double Visual Textual Transformer), approaches Subtasks 1 and 3 of Task 6 as multi-label classification problems, where the text and/or images of the meme are processed, and the probabilities of the presence of each possible persuasion technique are returned as a result. DVTT uses two complete networks of transformers that work on text and images that are mutually conditioned. One of the two modalities acts as the main one and the second one intervenes to enrich the first one, thus obtaining two distinct ways of operation. The two transformers outputs are merged by averaging the inferred probabilities for each possible label, and the overall network is trained end-to-end with a binary cross-entropy loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="messina-etal-2021-aimh">
<titleInfo>
<title>AIMH at SemEval-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Messina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrizio</namePart>
<namePart type="family">Falchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Gennaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Amato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system used by the AIMH Team to approach the SemEval Task 6. We propose an approach that relies on an architecture based on the transformer model to process multimodal content (text and images) in memes. Our architecture, called DVTT (Double Visual Textual Transformer), approaches Subtasks 1 and 3 of Task 6 as multi-label classification problems, where the text and/or images of the meme are processed, and the probabilities of the presence of each possible persuasion technique are returned as a result. DVTT uses two complete networks of transformers that work on text and images that are mutually conditioned. One of the two modalities acts as the main one and the second one intervenes to enrich the first one, thus obtaining two distinct ways of operation. The two transformers outputs are merged by averaging the inferred probabilities for each possible label, and the overall network is trained end-to-end with a binary cross-entropy loss.</abstract>
<identifier type="citekey">messina-etal-2021-aimh</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.140</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.140</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1020</start>
<end>1026</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AIMH at SemEval-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models
%A Messina, Nicola
%A Falchi, Fabrizio
%A Gennaro, Claudio
%A Amato, Giuseppe
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F messina-etal-2021-aimh
%X This paper describes the system used by the AIMH Team to approach the SemEval Task 6. We propose an approach that relies on an architecture based on the transformer model to process multimodal content (text and images) in memes. Our architecture, called DVTT (Double Visual Textual Transformer), approaches Subtasks 1 and 3 of Task 6 as multi-label classification problems, where the text and/or images of the meme are processed, and the probabilities of the presence of each possible persuasion technique are returned as a result. DVTT uses two complete networks of transformers that work on text and images that are mutually conditioned. One of the two modalities acts as the main one and the second one intervenes to enrich the first one, thus obtaining two distinct ways of operation. The two transformers outputs are merged by averaging the inferred probabilities for each possible label, and the overall network is trained end-to-end with a binary cross-entropy loss.
%R 10.18653/v1/2021.semeval-1.140
%U https://aclanthology.org/2021.semeval-1.140
%U https://doi.org/10.18653/v1/2021.semeval-1.140
%P 1020-1026
Markdown (Informal)
[AIMH at SemEval-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models](https://aclanthology.org/2021.semeval-1.140) (Messina et al., SemEval 2021)
ACL