@inproceedings{li-2021-codewithzichao-dravidianlangtech,
title = "Codewithzichao@{D}ravidian{L}ang{T}ech-{EACL}2021: Exploring Multimodal Transformers for Meme Classification in {T}amil Language",
author = "Li, Zichao",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.52/",
pages = "352--356",
abstract = "This paper describes our submission to shared task on Meme Classification for Tamil Language. To address this task, we explore a multimodal transformer for meme classification in Tamil language. According to the characteristics of the image and text, we use different pretrained models to encode the image and text so as to get better representations of the image and text respectively. Besides, we design a multimodal attention layer to make the text and corresponding image interact fully with each other based on cross attention. Our model achieved 0.55 weighted average F1 score and ranked first in this task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-2021-codewithzichao-dravidianlangtech">
<titleInfo>
<title>Codewithzichao@DravidianLangTech-EACL2021: Exploring Multimodal Transformers for Meme Classification in Tamil Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zichao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Kumar M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our submission to shared task on Meme Classification for Tamil Language. To address this task, we explore a multimodal transformer for meme classification in Tamil language. According to the characteristics of the image and text, we use different pretrained models to encode the image and text so as to get better representations of the image and text respectively. Besides, we design a multimodal attention layer to make the text and corresponding image interact fully with each other based on cross attention. Our model achieved 0.55 weighted average F1 score and ranked first in this task.</abstract>
<identifier type="citekey">li-2021-codewithzichao-dravidianlangtech</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.52/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>352</start>
<end>356</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Codewithzichao@DravidianLangTech-EACL2021: Exploring Multimodal Transformers for Meme Classification in Tamil Language
%A Li, Zichao
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F li-2021-codewithzichao-dravidianlangtech
%X This paper describes our submission to shared task on Meme Classification for Tamil Language. To address this task, we explore a multimodal transformer for meme classification in Tamil language. According to the characteristics of the image and text, we use different pretrained models to encode the image and text so as to get better representations of the image and text respectively. Besides, we design a multimodal attention layer to make the text and corresponding image interact fully with each other based on cross attention. Our model achieved 0.55 weighted average F1 score and ranked first in this task.
%U https://aclanthology.org/2021.dravidianlangtech-1.52/
%P 352-356
Markdown (Informal)
[Codewithzichao@DravidianLangTech-EACL2021: Exploring Multimodal Transformers for Meme Classification in Tamil Language](https://aclanthology.org/2021.dravidianlangtech-1.52/) (Li, DravidianLangTech 2021)
ACL