@inproceedings{acharya-etal-2025-paramananda,
title = "Paramananda@{NLU} of {D}evanagari Script Languages 2025: Detection of Language, Hate Speech and Targets using {F}ast{T}ext and {BERT}",
author = "Acharya, Darwin and
Dawadi, Sundeep and
Saud, Shivram and
Regmi, Sunil",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.39/",
pages = "334--338",
abstract = "This paper presents a comparative analysis of FastText and BERT-based approaches for Natural Language Understanding (NLU) tasks in Devanagari script languages. We evaluate these models on three critical tasks: language identification, hate speech detection, and target identification across five languages: Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Our experiments, although with raw tweet dataset but extracting only devanagari script, demonstrate that while both models achieve exceptional performance in language identification (F1 scores {\ensuremath{>}} 0.99), they show varying effectiveness in hate speech detection and target identification tasks. FastText with augmented data outperforms BERT in hate speech detection (F1 score: 0.8552 vs 0.5763), while BERT shows superior performance in target identification (F1 score: 0.5785 vs 0.4898). These findings contribute to the growing body of research on NLU for low-resource languages and provide insights into model selection for specific tasks in Devanagari script processing."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="acharya-etal-2025-paramananda">
<titleInfo>
<title>Paramananda@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech and Targets using FastText and BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darwin</namePart>
<namePart type="family">Acharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sundeep</namePart>
<namePart type="family">Dawadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivram</namePart>
<namePart type="family">Saud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a comparative analysis of FastText and BERT-based approaches for Natural Language Understanding (NLU) tasks in Devanagari script languages. We evaluate these models on three critical tasks: language identification, hate speech detection, and target identification across five languages: Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Our experiments, although with raw tweet dataset but extracting only devanagari script, demonstrate that while both models achieve exceptional performance in language identification (F1 scores \ensuremath> 0.99), they show varying effectiveness in hate speech detection and target identification tasks. FastText with augmented data outperforms BERT in hate speech detection (F1 score: 0.8552 vs 0.5763), while BERT shows superior performance in target identification (F1 score: 0.5785 vs 0.4898). These findings contribute to the growing body of research on NLU for low-resource languages and provide insights into model selection for specific tasks in Devanagari script processing.</abstract>
<identifier type="citekey">acharya-etal-2025-paramananda</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.39/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>334</start>
<end>338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paramananda@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech and Targets using FastText and BERT
%A Acharya, Darwin
%A Dawadi, Sundeep
%A Saud, Shivram
%A Regmi, Sunil
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F acharya-etal-2025-paramananda
%X This paper presents a comparative analysis of FastText and BERT-based approaches for Natural Language Understanding (NLU) tasks in Devanagari script languages. We evaluate these models on three critical tasks: language identification, hate speech detection, and target identification across five languages: Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Our experiments, although with raw tweet dataset but extracting only devanagari script, demonstrate that while both models achieve exceptional performance in language identification (F1 scores \ensuremath> 0.99), they show varying effectiveness in hate speech detection and target identification tasks. FastText with augmented data outperforms BERT in hate speech detection (F1 score: 0.8552 vs 0.5763), while BERT shows superior performance in target identification (F1 score: 0.5785 vs 0.4898). These findings contribute to the growing body of research on NLU for low-resource languages and provide insights into model selection for specific tasks in Devanagari script processing.
%U https://aclanthology.org/2025.chipsal-1.39/
%P 334-338
Markdown (Informal)
[Paramananda@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech and Targets using FastText and BERT](https://aclanthology.org/2025.chipsal-1.39/) (Acharya et al., CHiPSAL 2025)
ACL