@inproceedings{tahmid-etal-2025-pentaml,
title = "{P}enta{ML} at {BLP}-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for {B}angla Hate Speech Detection",
author = "Tahmid, Intesar and
Ahmed, Rafid and
Jawad, Md Mahir and
Uddin, Anam Borhan and
Fahim, Md and
Bhuiyan, Md Farhad Alam",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Hassan, Naeemul and
Hoque, Enamul and
Laskar, Md Tahmid Rahman and
Mohiuddin, Tasnim and
Rony, Md Rashad Al Hasan",
booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.banglalp-1.50/",
doi = "10.18653/v1/2025.banglalp-1.50",
pages = "538--543",
ISBN = "979-8-89176-314-2",
abstract = "This paper presents our approach for the BLP Shared Task 1, where we implemented Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection. The goal of the task was to customize the existing models so that they{'}re capable of automatically identifying hate speech in Bangla social media text, with a focus on YouTube comments. Our approach relied on fine-tuning several pre-trained BERT models, adapting them to the shared task dataset for improved classification accuracy. To further enhance performance, we applied linear probing on three of the fine-tuned models, enabling more effective utilization of the learned representations. The combination of these strategies resulted in a consistent top-15 ranking across all subtasks of the competition. Our findings highlight the effectiveness of linear probing as a lightweight yet impactful technique for enhancing hate speech detection in low-resource languages like Bangla."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahmid-etal-2025-pentaml">
<titleInfo>
<title>PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Intesar</namePart>
<namePart type="family">Tahmid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafid</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Mahir</namePart>
<namePart type="family">Jawad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anam</namePart>
<namePart type="given">Borhan</namePart>
<namePart type="family">Uddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="family">Fahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Farhad</namePart>
<namePart type="given">Alam</namePart>
<namePart type="family">Bhuiyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naeemul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tasnim</namePart>
<namePart type="family">Mohiuddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rashad</namePart>
<namePart type="given">Al</namePart>
<namePart type="given">Hasan</namePart>
<namePart type="family">Rony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-314-2</identifier>
</relatedItem>
<abstract>This paper presents our approach for the BLP Shared Task 1, where we implemented Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection. The goal of the task was to customize the existing models so that they’re capable of automatically identifying hate speech in Bangla social media text, with a focus on YouTube comments. Our approach relied on fine-tuning several pre-trained BERT models, adapting them to the shared task dataset for improved classification accuracy. To further enhance performance, we applied linear probing on three of the fine-tuned models, enabling more effective utilization of the learned representations. The combination of these strategies resulted in a consistent top-15 ranking across all subtasks of the competition. Our findings highlight the effectiveness of linear probing as a lightweight yet impactful technique for enhancing hate speech detection in low-resource languages like Bangla.</abstract>
<identifier type="citekey">tahmid-etal-2025-pentaml</identifier>
<identifier type="doi">10.18653/v1/2025.banglalp-1.50</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.50/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>538</start>
<end>543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection
%A Tahmid, Intesar
%A Ahmed, Rafid
%A Jawad, Md Mahir
%A Uddin, Anam Borhan
%A Fahim, Md
%A Bhuiyan, Md Farhad Alam
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Hoque, Enamul
%Y Laskar, Md Tahmid Rahman
%Y Mohiuddin, Tasnim
%Y Rony, Md Rashad Al Hasan
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F tahmid-etal-2025-pentaml
%X This paper presents our approach for the BLP Shared Task 1, where we implemented Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection. The goal of the task was to customize the existing models so that they’re capable of automatically identifying hate speech in Bangla social media text, with a focus on YouTube comments. Our approach relied on fine-tuning several pre-trained BERT models, adapting them to the shared task dataset for improved classification accuracy. To further enhance performance, we applied linear probing on three of the fine-tuned models, enabling more effective utilization of the learned representations. The combination of these strategies resulted in a consistent top-15 ranking across all subtasks of the competition. Our findings highlight the effectiveness of linear probing as a lightweight yet impactful technique for enhancing hate speech detection in low-resource languages like Bangla.
%R 10.18653/v1/2025.banglalp-1.50
%U https://aclanthology.org/2025.banglalp-1.50/
%U https://doi.org/10.18653/v1/2025.banglalp-1.50
%P 538-543
Markdown (Informal)
[PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection](https://aclanthology.org/2025.banglalp-1.50/) (Tahmid et al., BanglaLP 2025)
ACL