@inproceedings{r-etal-2026-hnk,
title = "{HNK}@{D}ravidian{L}ang{T}ech 2026: Investigating Grapheme-Level Normalization for Abusive {T}amil Text Classification",
author = "R, Hanish Vigneshwar and
Alaguraj, Nahul and
Manimaran, Karthikeyan and
Rajalakshmi, Ratnavel",
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-1.38/",
pages = "258--262",
ISBN = "979-8-89176-401-9",
abstract = "The increasing prevalence of social media has also correlated with an increase in abusive content targeting women, particularly for regional languages such as Tamil. The automatic identification of abusive content is critical for the creation of safer online spaces. In this paper, we focus on the abusive text detection of women in the context of binary text classification. We evaluated the performance of the proposed system on the abusive text detection of women using the IndicBERT, MuRIL, and Tamil-BERT models. Additionally, we propose the use of grapheme-aware normalization for the proposed system. Grapheme-aware normalization aims to maintain the structural integrity of Tamil characters at the Unicode level. The experimental results reveal that the proposed system using the Tamil-BERT model with grapheme-aware normalization achieves the best performance among the evaluated models. The proposed system achieved the third position in the shared task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="r-etal-2026-hnk">
<titleInfo>
<title>HNK@DravidianLangTech 2026: Investigating Grapheme-Level Normalization for Abusive Tamil Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanish</namePart>
<namePart type="given">Vigneshwar</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nahul</namePart>
<namePart type="family">Alaguraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthikeyan</namePart>
<namePart type="family">Manimaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnavel</namePart>
<namePart type="family">Rajalakshmi</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>The increasing prevalence of social media has also correlated with an increase in abusive content targeting women, particularly for regional languages such as Tamil. The automatic identification of abusive content is critical for the creation of safer online spaces. In this paper, we focus on the abusive text detection of women in the context of binary text classification. We evaluated the performance of the proposed system on the abusive text detection of women using the IndicBERT, MuRIL, and Tamil-BERT models. Additionally, we propose the use of grapheme-aware normalization for the proposed system. Grapheme-aware normalization aims to maintain the structural integrity of Tamil characters at the Unicode level. The experimental results reveal that the proposed system using the Tamil-BERT model with grapheme-aware normalization achieves the best performance among the evaluated models. The proposed system achieved the third position in the shared task.</abstract>
<identifier type="citekey">r-etal-2026-hnk</identifier>
<location>
<url>https://aclanthology.org/2026.dravidianlangtech-1.38/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>258</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HNK@DravidianLangTech 2026: Investigating Grapheme-Level Normalization for Abusive Tamil Text Classification
%A R, Hanish Vigneshwar
%A Alaguraj, Nahul
%A Manimaran, Karthikeyan
%A Rajalakshmi, Ratnavel
%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 r-etal-2026-hnk
%X The increasing prevalence of social media has also correlated with an increase in abusive content targeting women, particularly for regional languages such as Tamil. The automatic identification of abusive content is critical for the creation of safer online spaces. In this paper, we focus on the abusive text detection of women in the context of binary text classification. We evaluated the performance of the proposed system on the abusive text detection of women using the IndicBERT, MuRIL, and Tamil-BERT models. Additionally, we propose the use of grapheme-aware normalization for the proposed system. Grapheme-aware normalization aims to maintain the structural integrity of Tamil characters at the Unicode level. The experimental results reveal that the proposed system using the Tamil-BERT model with grapheme-aware normalization achieves the best performance among the evaluated models. The proposed system achieved the third position in the shared task.
%U https://aclanthology.org/2026.dravidianlangtech-1.38/
%P 258-262
Markdown (Informal)
[HNK@DravidianLangTech 2026: Investigating Grapheme-Level Normalization for Abusive Tamil Text Classification](https://aclanthology.org/2026.dravidianlangtech-1.38/) (R et al., DravidianLangTech 2026)
ACL