@inproceedings{francis-etal-2026-abusedetect,
title = "{A}buse{D}etect{\_}{A}lchemists@{D}ravidian{L}ang{T}ech 2026: A Weighted Transformer Ensemble for Detecting Abusive {T}amil Text Targeting Women",
author = "Francis, Meclin A and
Kumari, Jyoti and
Ulli, Vinay Babu and
Sreekumar, Malavika and
Johnson, Joel",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Rajiakodi, Saranya and
Navaneethakrishnan, Subalalitha and
Chinnappa, Dhivya and
Palani, Balasubramanian and
Subramanian, Malliga and
Shanmugavadivel, Kogilavani and
Rajalakshmi, Ratnavel",
booktitle = "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for {D}ravidian Languages",
month = jul,
year = "2026",
address = "Underline (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dravidianlangtech-1.16/",
pages = "144--147",
ISBN = "979-8-89176-401-9",
abstract = "This paper describes our system submitted to the shared task on Abusive Tamil Text Targeting Women on Social Media at DravidianLangTech@ACL 2026. We formulate the problem as a supervised binary classification task, assigning each Tamil social media comment to an Abusive or Non-Abusive category. Our pipeline begins with a tailored preprocessing stage that handles emoji translation, URL removal, and entity normalization. We then independently fine-tune two pre-trained transformer models MuRIL and XLM-RoBERTa on the task data. At inference time, we combine these models through a weighted softmax ensemble, assigning a weight of 0.6 to MuRIL and 0.4 to XLM-RoBERTa. The resulting system achieves a Macro-F1 score of 0.8115 on the test set, outperforming both individual models. The code is publicly available at: https://github.com/meclin2345/AbuseDetect{\_}Alchemists"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="francis-etal-2026-abusedetect">
<titleInfo>
<title>AbuseDetect_Alchemists@DravidianLangTech 2026: A Weighted Transformer Ensemble for Detecting Abusive Tamil Text Targeting Women</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meclin</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Francis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyoti</namePart>
<namePart type="family">Kumari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinay</namePart>
<namePart type="given">Babu</namePart>
<namePart type="family">Ulli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malavika</namePart>
<namePart type="family">Sreekumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Speech, Vision, 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="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Navaneethakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kogilavani</namePart>
<namePart type="family">Shanmugavadivel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnavel</namePart>
<namePart type="family">Rajalakshmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Underline (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-401-9</identifier>
</relatedItem>
<abstract>This paper describes our system submitted to the shared task on Abusive Tamil Text Targeting Women on Social Media at DravidianLangTech@ACL 2026. We formulate the problem as a supervised binary classification task, assigning each Tamil social media comment to an Abusive or Non-Abusive category. Our pipeline begins with a tailored preprocessing stage that handles emoji translation, URL removal, and entity normalization. We then independently fine-tune two pre-trained transformer models MuRIL and XLM-RoBERTa on the task data. At inference time, we combine these models through a weighted softmax ensemble, assigning a weight of 0.6 to MuRIL and 0.4 to XLM-RoBERTa. The resulting system achieves a Macro-F1 score of 0.8115 on the test set, outperforming both individual models. The code is publicly available at: https://github.com/meclin2345/AbuseDetect_Alchemists</abstract>
<identifier type="citekey">francis-etal-2026-abusedetect</identifier>
<location>
<url>https://aclanthology.org/2026.dravidianlangtech-1.16/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>144</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AbuseDetect_Alchemists@DravidianLangTech 2026: A Weighted Transformer Ensemble for Detecting Abusive Tamil Text Targeting Women
%A Francis, Meclin A.
%A Kumari, Jyoti
%A Ulli, Vinay Babu
%A Sreekumar, Malavika
%A Johnson, Joel
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Rajiakodi, Saranya
%Y Navaneethakrishnan, Subalalitha
%Y Chinnappa, Dhivya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Shanmugavadivel, Kogilavani
%Y Rajalakshmi, Ratnavel
%S Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2026
%8 July
%I Association for Computational Linguistics
%C Underline (Virtual)
%@ 979-8-89176-401-9
%F francis-etal-2026-abusedetect
%X This paper describes our system submitted to the shared task on Abusive Tamil Text Targeting Women on Social Media at DravidianLangTech@ACL 2026. We formulate the problem as a supervised binary classification task, assigning each Tamil social media comment to an Abusive or Non-Abusive category. Our pipeline begins with a tailored preprocessing stage that handles emoji translation, URL removal, and entity normalization. We then independently fine-tune two pre-trained transformer models MuRIL and XLM-RoBERTa on the task data. At inference time, we combine these models through a weighted softmax ensemble, assigning a weight of 0.6 to MuRIL and 0.4 to XLM-RoBERTa. The resulting system achieves a Macro-F1 score of 0.8115 on the test set, outperforming both individual models. The code is publicly available at: https://github.com/meclin2345/AbuseDetect_Alchemists
%U https://aclanthology.org/2026.dravidianlangtech-1.16/
%P 144-147
Markdown (Informal)
[AbuseDetect_Alchemists@DravidianLangTech 2026: A Weighted Transformer Ensemble for Detecting Abusive Tamil Text Targeting Women](https://aclanthology.org/2026.dravidianlangtech-1.16/) (Francis et al., DravidianLangTech 2026)
ACL