@inproceedings{bansal-etal-2026-ethosai,
title = "{E}thos{AI}@{CH}i{PSAL}2026: Hate and Sentiment Understanding in Low-Resource Memes Using a Multimodal Approach",
author = "Bansal, Vinayak and
Sharma, Deepawali and
Singh, Aakash and
Singh, Vivek Kumar",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini",
booktitle = "Proceedings of the Second workshop on Challenges in Processing {S}outh {A}sian Languages ({CH}i{PSAL}2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.chipsal-1.33/",
doi = "10.63317/576er6z44zrx",
pages = "316--323",
abstract = "Memes have become a popular way for people to share opinions and emotions on social media, but they are also often used to spread hate and negative sentiments. In this paper, we present our multimodal approach to the CHiPSAL 2026 shared task on multimodal hate and sentiment detection in Nepali memes, which includes two subtasks: hate detection and sentiment analysis. Since memes usually combine both text and images, we first experimented with different unimodal models for text and images separately. After identifying the top two best-performing text and image models, combined them using different fusion techniques. The results show that multimodal models outperform unimodal ones, highlighting that both textual and visual information are important for understanding the context of memes. The multi- modal model, which combines sentence-transformers/LaBSE for text and ResNet-18 for image using weighted Fusion technique, achieved a macro F1 score of 0.6614 for Subtask A and sentence-Transformers/LaBSE for text and deit- Base for image using simple Fusion technique, achieved a macro F1 score of 0.4839 for SubTask B, on the test dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-etal-2026-ethosai">
<titleInfo>
<title>EthosAI@CHiPSAL2026: Hate and Sentiment Understanding in Low-Resource Memes Using a Multimodal Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vinayak</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepawali</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakash</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Memes have become a popular way for people to share opinions and emotions on social media, but they are also often used to spread hate and negative sentiments. In this paper, we present our multimodal approach to the CHiPSAL 2026 shared task on multimodal hate and sentiment detection in Nepali memes, which includes two subtasks: hate detection and sentiment analysis. Since memes usually combine both text and images, we first experimented with different unimodal models for text and images separately. After identifying the top two best-performing text and image models, combined them using different fusion techniques. The results show that multimodal models outperform unimodal ones, highlighting that both textual and visual information are important for understanding the context of memes. The multi- modal model, which combines sentence-transformers/LaBSE for text and ResNet-18 for image using weighted Fusion technique, achieved a macro F1 score of 0.6614 for Subtask A and sentence-Transformers/LaBSE for text and deit- Base for image using simple Fusion technique, achieved a macro F1 score of 0.4839 for SubTask B, on the test dataset.</abstract>
<identifier type="citekey">bansal-etal-2026-ethosai</identifier>
<identifier type="doi">10.63317/576er6z44zrx</identifier>
<location>
<url>https://aclanthology.org/2026.chipsal-1.33/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>316</start>
<end>323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EthosAI@CHiPSAL2026: Hate and Sentiment Understanding in Low-Resource Memes Using a Multimodal Approach
%A Bansal, Vinayak
%A Sharma, Deepawali
%A Singh, Aakash
%A Singh, Vivek Kumar
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F bansal-etal-2026-ethosai
%X Memes have become a popular way for people to share opinions and emotions on social media, but they are also often used to spread hate and negative sentiments. In this paper, we present our multimodal approach to the CHiPSAL 2026 shared task on multimodal hate and sentiment detection in Nepali memes, which includes two subtasks: hate detection and sentiment analysis. Since memes usually combine both text and images, we first experimented with different unimodal models for text and images separately. After identifying the top two best-performing text and image models, combined them using different fusion techniques. The results show that multimodal models outperform unimodal ones, highlighting that both textual and visual information are important for understanding the context of memes. The multi- modal model, which combines sentence-transformers/LaBSE for text and ResNet-18 for image using weighted Fusion technique, achieved a macro F1 score of 0.6614 for Subtask A and sentence-Transformers/LaBSE for text and deit- Base for image using simple Fusion technique, achieved a macro F1 score of 0.4839 for SubTask B, on the test dataset.
%R 10.63317/576er6z44zrx
%U https://aclanthology.org/2026.chipsal-1.33/
%U https://doi.org/10.63317/576er6z44zrx
%P 316-323
Markdown (Informal)
[EthosAI@CHiPSAL2026: Hate and Sentiment Understanding in Low-Resource Memes Using a Multimodal Approach](https://aclanthology.org/2026.chipsal-1.33/) (Bansal et al., CHiPSAL 2026)
ACL