@inproceedings{dhamecha-etal-2025-team-horizon,
title = "Team Horizon at {BHASHA} Task 2: Fine-tuning Multilingual Transformers for {I}ndic Word Grouping",
author = "Dhamecha, Manav and
Damor, Gaurav and
Jaat, Sunil and
Mishra, Pruthwik",
editor = "Bhattacharya, Arnab and
Goyal, Pawan and
Ghosh, Saptarshi and
Ghosh, Kripabandhu",
booktitle = "Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bhasha-1.18/",
pages = "175--179",
ISBN = "979-8-89176-313-5",
abstract = "We present Team Horizon{'}s approach to BHASHA Task 2: Indic Word Grouping. We model the word-grouping problem as token classification problem and fine-tune multilingual Transformer encoders for the task. We evaluated MuRIL, XLM-Roberta, and IndicBERT v2 and report Exact Match accuracy on the test data. Our best model (MuRIL) achieves 58.1818{\%} exact match on the test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhamecha-etal-2025-team-horizon">
<titleInfo>
<title>Team Horizon at BHASHA Task 2: Fine-tuning Multilingual Transformers for Indic Word Grouping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manav</namePart>
<namePart type="family">Dhamecha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Damor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Jaat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</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 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kripabandhu</namePart>
<namePart type="family">Ghosh</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">979-8-89176-313-5</identifier>
</relatedItem>
<abstract>We present Team Horizon’s approach to BHASHA Task 2: Indic Word Grouping. We model the word-grouping problem as token classification problem and fine-tune multilingual Transformer encoders for the task. We evaluated MuRIL, XLM-Roberta, and IndicBERT v2 and report Exact Match accuracy on the test data. Our best model (MuRIL) achieves 58.1818% exact match on the test set.</abstract>
<identifier type="citekey">dhamecha-etal-2025-team-horizon</identifier>
<location>
<url>https://aclanthology.org/2025.bhasha-1.18/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>175</start>
<end>179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team Horizon at BHASHA Task 2: Fine-tuning Multilingual Transformers for Indic Word Grouping
%A Dhamecha, Manav
%A Damor, Gaurav
%A Jaat, Sunil
%A Mishra, Pruthwik
%Y Bhattacharya, Arnab
%Y Goyal, Pawan
%Y Ghosh, Saptarshi
%Y Ghosh, Kripabandhu
%S Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-313-5
%F dhamecha-etal-2025-team-horizon
%X We present Team Horizon’s approach to BHASHA Task 2: Indic Word Grouping. We model the word-grouping problem as token classification problem and fine-tune multilingual Transformer encoders for the task. We evaluated MuRIL, XLM-Roberta, and IndicBERT v2 and report Exact Match accuracy on the test data. Our best model (MuRIL) achieves 58.1818% exact match on the test set.
%U https://aclanthology.org/2025.bhasha-1.18/
%P 175-179
Markdown (Informal)
[Team Horizon at BHASHA Task 2: Fine-tuning Multilingual Transformers for Indic Word Grouping](https://aclanthology.org/2025.bhasha-1.18/) (Dhamecha et al., BHASHA 2025)
ACL