@inproceedings{sharma-etal-2022-domain,
title = "Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis",
author = "Sharma, Shivam and
Siddiqui, Mohd Khizir and
Akhtar, Md. Shad and
Chakraborty, Tanmoy",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.60",
pages = "792--805",
abstract = "Existing self-supervised learning strategies are constrained to either a limited set of objectives or generic downstream tasks that predominantly target uni-modal applications. This has isolated progress for imperative multi-modal applications that are diverse in terms of complexity and domain-affinity, such as meme analysis. Here, we introduce two self-supervised pre-training methods, namely Ext-PIE-Net and MM-SimCLR that (i) employ off-the-shelf multi-modal hate-speech data during pre-training and (ii) perform self-supervised learning by incorporating multiple specialized pretext tasks, effectively catering to the required complex multi-modal representation learning for meme analysis. We experiment with different self-supervision strategies, including potential variants that could help learn rich cross-modality representations and evaluate using popular linear probing on the Hateful Memes task. The proposed solutions strongly compete with the fully supervised baseline via label-efficient training while distinctly outperforming them on all three tasks of the Memotion challenge with 0.18{\%}, 23.64{\%}, and 0.93{\%} performance gain, respectively. Further, we demonstrate the generalizability of the proposed solutions by reporting competitive performance on the HarMeme task. Finally, we empirically establish the quality of the learned representations by analyzing task-specific learning, using fewer labeled training samples, and arguing that the complexity of the self-supervision strategy and downstream task at hand are correlated. Our efforts highlight the requirement of better multi-modal self-supervision methods involving specialized pretext tasks for efficient fine-tuning and generalizable performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2022-domain">
<titleInfo>
<title>Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivam</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohd</namePart>
<namePart type="given">Khizir</namePart>
<namePart type="family">Siddiqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing self-supervised learning strategies are constrained to either a limited set of objectives or generic downstream tasks that predominantly target uni-modal applications. This has isolated progress for imperative multi-modal applications that are diverse in terms of complexity and domain-affinity, such as meme analysis. Here, we introduce two self-supervised pre-training methods, namely Ext-PIE-Net and MM-SimCLR that (i) employ off-the-shelf multi-modal hate-speech data during pre-training and (ii) perform self-supervised learning by incorporating multiple specialized pretext tasks, effectively catering to the required complex multi-modal representation learning for meme analysis. We experiment with different self-supervision strategies, including potential variants that could help learn rich cross-modality representations and evaluate using popular linear probing on the Hateful Memes task. The proposed solutions strongly compete with the fully supervised baseline via label-efficient training while distinctly outperforming them on all three tasks of the Memotion challenge with 0.18%, 23.64%, and 0.93% performance gain, respectively. Further, we demonstrate the generalizability of the proposed solutions by reporting competitive performance on the HarMeme task. Finally, we empirically establish the quality of the learned representations by analyzing task-specific learning, using fewer labeled training samples, and arguing that the complexity of the self-supervision strategy and downstream task at hand are correlated. Our efforts highlight the requirement of better multi-modal self-supervision methods involving specialized pretext tasks for efficient fine-tuning and generalizable performance.</abstract>
<identifier type="citekey">sharma-etal-2022-domain</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.60</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>792</start>
<end>805</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
%A Sharma, Shivam
%A Siddiqui, Mohd Khizir
%A Akhtar, Md. Shad
%A Chakraborty, Tanmoy
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F sharma-etal-2022-domain
%X Existing self-supervised learning strategies are constrained to either a limited set of objectives or generic downstream tasks that predominantly target uni-modal applications. This has isolated progress for imperative multi-modal applications that are diverse in terms of complexity and domain-affinity, such as meme analysis. Here, we introduce two self-supervised pre-training methods, namely Ext-PIE-Net and MM-SimCLR that (i) employ off-the-shelf multi-modal hate-speech data during pre-training and (ii) perform self-supervised learning by incorporating multiple specialized pretext tasks, effectively catering to the required complex multi-modal representation learning for meme analysis. We experiment with different self-supervision strategies, including potential variants that could help learn rich cross-modality representations and evaluate using popular linear probing on the Hateful Memes task. The proposed solutions strongly compete with the fully supervised baseline via label-efficient training while distinctly outperforming them on all three tasks of the Memotion challenge with 0.18%, 23.64%, and 0.93% performance gain, respectively. Further, we demonstrate the generalizability of the proposed solutions by reporting competitive performance on the HarMeme task. Finally, we empirically establish the quality of the learned representations by analyzing task-specific learning, using fewer labeled training samples, and arguing that the complexity of the self-supervision strategy and downstream task at hand are correlated. Our efforts highlight the requirement of better multi-modal self-supervision methods involving specialized pretext tasks for efficient fine-tuning and generalizable performance.
%U https://aclanthology.org/2022.aacl-main.60
%P 792-805
Markdown (Informal)
[Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis](https://aclanthology.org/2022.aacl-main.60) (Sharma et al., AACL-IJCNLP 2022)
ACL
- Shivam Sharma, Mohd Khizir Siddiqui, Md. Shad Akhtar, and Tanmoy Chakraborty. 2022. Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 792–805, Online only. Association for Computational Linguistics.