@inproceedings{vlad-etal-2020-upb,
title = "{UPB} at {S}em{E}val-2020 Task 8: Joint Textual and Visual Modeling in a Multi-Task Learning Architecture for Memotion Analysis",
author = "Vlad, George-Alexandru and
Zaharia, George-Eduard and
Cercel, Dumitru-Clementin and
Chiru, Costin and
Trausan-Matu, Stefan",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.160/",
doi = "10.18653/v1/2020.semeval-1.160",
pages = "1208--1214",
abstract = "Users from the online environment can create different ways of expressing their thoughts, opinions, or conception of amusement. Internet memes were created specifically for these situations. Their main purpose is to transmit ideas by using combinations of images and texts such that they will create a certain state for the receptor, depending on the message the meme has to send. These posts can be related to various situations or events, thus adding a funny side to any circumstance our world is situated in. In this paper, we describe the system developed by our team for SemEval-2020 Task 8: Memotion Analysis. More specifically, we introduce a novel system to analyze these posts, a multimodal multi-task learning architecture that combines ALBERT for text encoding with VGG-16 for image representation. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the three subtasks of the current competition, ranking 11th for Subtask A (0.3453 macro F1-score), 1st for Subtask B (0.5183 macro F1-score), and 3rd for Subtask C (0.3171 macro F1-score) while exceeding the official baseline results by high margins."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vlad-etal-2020-upb">
<titleInfo>
<title>UPB at SemEval-2020 Task 8: Joint Textual and Visual Modeling in a Multi-Task Learning Architecture for Memotion Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">George-Alexandru</namePart>
<namePart type="family">Vlad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George-Eduard</namePart>
<namePart type="family">Zaharia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costin</namePart>
<namePart type="family">Chiru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Trausan-Matu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Users from the online environment can create different ways of expressing their thoughts, opinions, or conception of amusement. Internet memes were created specifically for these situations. Their main purpose is to transmit ideas by using combinations of images and texts such that they will create a certain state for the receptor, depending on the message the meme has to send. These posts can be related to various situations or events, thus adding a funny side to any circumstance our world is situated in. In this paper, we describe the system developed by our team for SemEval-2020 Task 8: Memotion Analysis. More specifically, we introduce a novel system to analyze these posts, a multimodal multi-task learning architecture that combines ALBERT for text encoding with VGG-16 for image representation. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the three subtasks of the current competition, ranking 11th for Subtask A (0.3453 macro F1-score), 1st for Subtask B (0.5183 macro F1-score), and 3rd for Subtask C (0.3171 macro F1-score) while exceeding the official baseline results by high margins.</abstract>
<identifier type="citekey">vlad-etal-2020-upb</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.160</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.160/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1208</start>
<end>1214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPB at SemEval-2020 Task 8: Joint Textual and Visual Modeling in a Multi-Task Learning Architecture for Memotion Analysis
%A Vlad, George-Alexandru
%A Zaharia, George-Eduard
%A Cercel, Dumitru-Clementin
%A Chiru, Costin
%A Trausan-Matu, Stefan
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F vlad-etal-2020-upb
%X Users from the online environment can create different ways of expressing their thoughts, opinions, or conception of amusement. Internet memes were created specifically for these situations. Their main purpose is to transmit ideas by using combinations of images and texts such that they will create a certain state for the receptor, depending on the message the meme has to send. These posts can be related to various situations or events, thus adding a funny side to any circumstance our world is situated in. In this paper, we describe the system developed by our team for SemEval-2020 Task 8: Memotion Analysis. More specifically, we introduce a novel system to analyze these posts, a multimodal multi-task learning architecture that combines ALBERT for text encoding with VGG-16 for image representation. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the three subtasks of the current competition, ranking 11th for Subtask A (0.3453 macro F1-score), 1st for Subtask B (0.5183 macro F1-score), and 3rd for Subtask C (0.3171 macro F1-score) while exceeding the official baseline results by high margins.
%R 10.18653/v1/2020.semeval-1.160
%U https://aclanthology.org/2020.semeval-1.160/
%U https://doi.org/10.18653/v1/2020.semeval-1.160
%P 1208-1214
Markdown (Informal)
[UPB at SemEval-2020 Task 8: Joint Textual and Visual Modeling in a Multi-Task Learning Architecture for Memotion Analysis](https://aclanthology.org/2020.semeval-1.160/) (Vlad et al., SemEval 2020)
ACL