@inproceedings{dey-etal-2023-semantics,
title = "Semantics Squad at {BLP}-2023 Task 1: Violence Inciting {B}angla Text Detection with Fine-Tuned Transformer-Based Models",
author = "Dey, Krishno and
Tarannum, Prerona and
Hasan, Md. Arid and
Palma, Francis",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Sadeque, Farig and
Amin, Ruhul",
booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.banglalp-1.28",
doi = "10.18653/v1/2023.banglalp-1.28",
pages = "225--229",
abstract = "This study investigates the application of Transformer-based models for violence threat identification. We participated in the BLP-2023 Shared Task 1 and in our initial submission, BanglaBERT large achieved 5th position on the leader-board with a macro F1 score of 0.7441, approaching the highest baseline of 0.7879 established for this task. In contrast, the top-performing system on the leaderboard achieved an F1 score of 0.7604. Subsequent experiments involving m-BERT, XLM-RoBERTa base, XLM-RoBERTa large, BanglishBERT, BanglaBERT, and BanglaBERT large models revealed that BanglaBERT achieved an F1 score of 0.7441, which closely approximated the baseline. Remarkably, m-BERT and XLM-RoBERTa base also approximated the baseline with macro F1 scores of 0.6584 and 0.6968, respectively. A notable finding from our study is the under-performance by larger models for the shared task dataset, which requires further investigation. Our findings underscore the potential of transformer-based models in identifying violence threats, offering valuable insights to enhance safety measures on online platforms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dey-etal-2023-semantics">
<titleInfo>
<title>Semantics Squad at BLP-2023 Task 1: Violence Inciting Bangla Text Detection with Fine-Tuned Transformer-Based Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishno</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prerona</namePart>
<namePart type="family">Tarannum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Arid</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Palma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)</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">Farig</namePart>
<namePart type="family">Sadeque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study investigates the application of Transformer-based models for violence threat identification. We participated in the BLP-2023 Shared Task 1 and in our initial submission, BanglaBERT large achieved 5th position on the leader-board with a macro F1 score of 0.7441, approaching the highest baseline of 0.7879 established for this task. In contrast, the top-performing system on the leaderboard achieved an F1 score of 0.7604. Subsequent experiments involving m-BERT, XLM-RoBERTa base, XLM-RoBERTa large, BanglishBERT, BanglaBERT, and BanglaBERT large models revealed that BanglaBERT achieved an F1 score of 0.7441, which closely approximated the baseline. Remarkably, m-BERT and XLM-RoBERTa base also approximated the baseline with macro F1 scores of 0.6584 and 0.6968, respectively. A notable finding from our study is the under-performance by larger models for the shared task dataset, which requires further investigation. Our findings underscore the potential of transformer-based models in identifying violence threats, offering valuable insights to enhance safety measures on online platforms.</abstract>
<identifier type="citekey">dey-etal-2023-semantics</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.28</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.28</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>225</start>
<end>229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantics Squad at BLP-2023 Task 1: Violence Inciting Bangla Text Detection with Fine-Tuned Transformer-Based Models
%A Dey, Krishno
%A Tarannum, Prerona
%A Hasan, Md. Arid
%A Palma, Francis
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Sadeque, Farig
%Y Amin, Ruhul
%S Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F dey-etal-2023-semantics
%X This study investigates the application of Transformer-based models for violence threat identification. We participated in the BLP-2023 Shared Task 1 and in our initial submission, BanglaBERT large achieved 5th position on the leader-board with a macro F1 score of 0.7441, approaching the highest baseline of 0.7879 established for this task. In contrast, the top-performing system on the leaderboard achieved an F1 score of 0.7604. Subsequent experiments involving m-BERT, XLM-RoBERTa base, XLM-RoBERTa large, BanglishBERT, BanglaBERT, and BanglaBERT large models revealed that BanglaBERT achieved an F1 score of 0.7441, which closely approximated the baseline. Remarkably, m-BERT and XLM-RoBERTa base also approximated the baseline with macro F1 scores of 0.6584 and 0.6968, respectively. A notable finding from our study is the under-performance by larger models for the shared task dataset, which requires further investigation. Our findings underscore the potential of transformer-based models in identifying violence threats, offering valuable insights to enhance safety measures on online platforms.
%R 10.18653/v1/2023.banglalp-1.28
%U https://aclanthology.org/2023.banglalp-1.28
%U https://doi.org/10.18653/v1/2023.banglalp-1.28
%P 225-229
Markdown (Informal)
[Semantics Squad at BLP-2023 Task 1: Violence Inciting Bangla Text Detection with Fine-Tuned Transformer-Based Models](https://aclanthology.org/2023.banglalp-1.28) (Dey et al., BanglaLP 2023)
ACL