@inproceedings{riyad-etal-2023-team,
title = "{T}eam{\_}{S}yrax at {BLP}-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in {B}angla",
author = "Riyad, Omar Faruqe and
Chakraborty, Trina and
Dey, Abhishek",
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-1.32",
doi = "10.18653/v1/2023.banglalp-1.32",
pages = "247--254",
abstract = "This paper describes our participation in Task1 (VITD) of BLP Workshop 1 at EMNLP 2023,focused on the detection and categorizationof threats linked to violence, which could po-tentially encourage more violent actions. Ourapproach involves fine-tuning of pre-trainedtransformer models and employing techniqueslike self-training with external data, data aug-mentation through back-translation, and en-semble learning (bagging and majority voting).Notably, self-training improves performancewhen applied to data from external source butnot when applied to the test-set. Our anal-ysis highlights the effectiveness of ensemblemethods and data augmentation techniques inBangla Text Classification. Our system ini-tially scored 0.70450 and ranked 19th amongthe participants but post-competition experi-ments boosted our score to 0.72740.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riyad-etal-2023-team">
<titleInfo>
<title>Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="given">Faruqe</namePart>
<namePart type="family">Riyad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trina</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Dey</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 paper describes our participation in Task1 (VITD) of BLP Workshop 1 at EMNLP 2023,focused on the detection and categorizationof threats linked to violence, which could po-tentially encourage more violent actions. Ourapproach involves fine-tuning of pre-trainedtransformer models and employing techniqueslike self-training with external data, data aug-mentation through back-translation, and en-semble learning (bagging and majority voting).Notably, self-training improves performancewhen applied to data from external source butnot when applied to the test-set. Our anal-ysis highlights the effectiveness of ensemblemethods and data augmentation techniques inBangla Text Classification. Our system ini-tially scored 0.70450 and ranked 19th amongthe participants but post-competition experi-ments boosted our score to 0.72740.</abstract>
<identifier type="citekey">riyad-etal-2023-team</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.32</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.32</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>247</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla
%A Riyad, Omar Faruqe
%A Chakraborty, Trina
%A Dey, Abhishek
%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 riyad-etal-2023-team
%X This paper describes our participation in Task1 (VITD) of BLP Workshop 1 at EMNLP 2023,focused on the detection and categorizationof threats linked to violence, which could po-tentially encourage more violent actions. Ourapproach involves fine-tuning of pre-trainedtransformer models and employing techniqueslike self-training with external data, data aug-mentation through back-translation, and en-semble learning (bagging and majority voting).Notably, self-training improves performancewhen applied to data from external source butnot when applied to the test-set. Our anal-ysis highlights the effectiveness of ensemblemethods and data augmentation techniques inBangla Text Classification. Our system ini-tially scored 0.70450 and ranked 19th amongthe participants but post-competition experi-ments boosted our score to 0.72740.
%R 10.18653/v1/2023.banglalp-1.32
%U https://aclanthology.org/2023.banglalp-1.32
%U https://doi.org/10.18653/v1/2023.banglalp-1.32
%P 247-254
Markdown (Informal)
[Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla](https://aclanthology.org/2023.banglalp-1.32) (Riyad et al., BanglaLP 2023)
ACL