@inproceedings{morishita-etal-2020-hitachi-semeval-2020,
title = "Hitachi at {S}em{E}val-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition",
author = "Morishita, Terufumi and
Morio, Gaku and
Horiguchi, Shota and
Ozaki, Hiroaki and
Miyoshi, Toshinori",
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-1.149",
doi = "10.18653/v1/2020.semeval-1.149",
pages = "1126--1134",
abstract = "Users of social networking services often share their emotions via multi-modal content, usually images paired with text embedded in them. SemEval-2020 task 8, Memotion Analysis, aims at automatically recognizing these emotions of so-called internet memes. In this paper, we propose a simple but effective Modality Ensemble that incorporates visual and textual deep-learning models, which are independently trained, rather than providing a single multi-modal joint network. To this end, we first fine-tune four pre-trained visual models (i.e., Inception-ResNet, PolyNet, SENet, and PNASNet) and four textual models (i.e., BERT, GPT-2, Transformer-XL, and XLNet). Then, we fuse their predictions with ensemble methods to effectively capture cross-modal correlations. The experiments performed on dev-set show that both visual and textual features aided each other, especially in subtask-C, and consequently, our system ranked 2nd on subtask-C.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morishita-etal-2020-hitachi-semeval-2020">
<titleInfo>
<title>Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Terufumi</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shota</namePart>
<namePart type="family">Horiguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshinori</namePart>
<namePart type="family">Miyoshi</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 of social networking services often share their emotions via multi-modal content, usually images paired with text embedded in them. SemEval-2020 task 8, Memotion Analysis, aims at automatically recognizing these emotions of so-called internet memes. In this paper, we propose a simple but effective Modality Ensemble that incorporates visual and textual deep-learning models, which are independently trained, rather than providing a single multi-modal joint network. To this end, we first fine-tune four pre-trained visual models (i.e., Inception-ResNet, PolyNet, SENet, and PNASNet) and four textual models (i.e., BERT, GPT-2, Transformer-XL, and XLNet). Then, we fuse their predictions with ensemble methods to effectively capture cross-modal correlations. The experiments performed on dev-set show that both visual and textual features aided each other, especially in subtask-C, and consequently, our system ranked 2nd on subtask-C.</abstract>
<identifier type="citekey">morishita-etal-2020-hitachi-semeval-2020</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.149</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.149</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1126</start>
<end>1134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition
%A Morishita, Terufumi
%A Morio, Gaku
%A Horiguchi, Shota
%A Ozaki, Hiroaki
%A Miyoshi, Toshinori
%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 morishita-etal-2020-hitachi-semeval-2020
%X Users of social networking services often share their emotions via multi-modal content, usually images paired with text embedded in them. SemEval-2020 task 8, Memotion Analysis, aims at automatically recognizing these emotions of so-called internet memes. In this paper, we propose a simple but effective Modality Ensemble that incorporates visual and textual deep-learning models, which are independently trained, rather than providing a single multi-modal joint network. To this end, we first fine-tune four pre-trained visual models (i.e., Inception-ResNet, PolyNet, SENet, and PNASNet) and four textual models (i.e., BERT, GPT-2, Transformer-XL, and XLNet). Then, we fuse their predictions with ensemble methods to effectively capture cross-modal correlations. The experiments performed on dev-set show that both visual and textual features aided each other, especially in subtask-C, and consequently, our system ranked 2nd on subtask-C.
%R 10.18653/v1/2020.semeval-1.149
%U https://aclanthology.org/2020.semeval-1.149
%U https://doi.org/10.18653/v1/2020.semeval-1.149
%P 1126-1134
Markdown (Informal)
[Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition](https://aclanthology.org/2020.semeval-1.149) (Morishita et al., SemEval 2020)
ACL