@inproceedings{bhattacharyya-etal-2025-findings,
title = "Findings of the {I}ndic{GEC} and {I}ndic{WG} Shared Task at {BHASHA} 2025",
author = "Bhattacharyya, Pramit and
N J, Karthika and
Terdalkar, Hrishikesh and
Jagadeeshan, Manoj Balaji and
Nigam, Shubham Kumar and
Susmitha, Arvapalli Sai and
Bhattacharya, Arnab",
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-1.12/",
pages = "127--134",
ISBN = "979-8-89176-313-5",
abstract = "This overview paper presents the findings of the two shared tasks organized as part of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA) co-located with IJCNLP-AACL 2025. The shared tasks are: (1) Indic Grammar Error Correction (IndicGEC) and (2) Indic Word Grouping (IndicWG). For GEC, participants were tasked with producing grammatically correct sentences based on given input sentences in five Indian languages. For WG, participants were required to generate a word-grouped variant of a provided sentence in Hindi. The evaluation metric used for GEC was GLEU, while Exact Matching was employed for WG. A total of 14 teams participated in the final phase of the Shared Task 1; 2 teams participated in the final phase of Shared Task 2. The maximum GLEU scores obtained for Hindi, Bangla, Telugu, Tamil and Malayalam languages are respectively 85.69, 95.79, 88.17, 91.57 and 96.02 for the IndicGEC shared task. The highest exact matching score obtained for IndicWG shared task is 45.13{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharyya-etal-2025-findings">
<titleInfo>
<title>Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pramit</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthika</namePart>
<namePart type="family">N J</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrishikesh</namePart>
<namePart type="family">Terdalkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="given">Balaji</namePart>
<namePart type="family">Jagadeeshan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Nigam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvapalli</namePart>
<namePart type="given">Sai</namePart>
<namePart type="family">Susmitha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Bhattacharya</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>This overview paper presents the findings of the two shared tasks organized as part of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA) co-located with IJCNLP-AACL 2025. The shared tasks are: (1) Indic Grammar Error Correction (IndicGEC) and (2) Indic Word Grouping (IndicWG). For GEC, participants were tasked with producing grammatically correct sentences based on given input sentences in five Indian languages. For WG, participants were required to generate a word-grouped variant of a provided sentence in Hindi. The evaluation metric used for GEC was GLEU, while Exact Matching was employed for WG. A total of 14 teams participated in the final phase of the Shared Task 1; 2 teams participated in the final phase of Shared Task 2. The maximum GLEU scores obtained for Hindi, Bangla, Telugu, Tamil and Malayalam languages are respectively 85.69, 95.79, 88.17, 91.57 and 96.02 for the IndicGEC shared task. The highest exact matching score obtained for IndicWG shared task is 45.13%.</abstract>
<identifier type="citekey">bhattacharyya-etal-2025-findings</identifier>
<location>
<url>https://aclanthology.org/2025.bhasha-1.12/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>127</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025
%A Bhattacharyya, Pramit
%A N J, Karthika
%A Terdalkar, Hrishikesh
%A Jagadeeshan, Manoj Balaji
%A Nigam, Shubham Kumar
%A Susmitha, Arvapalli Sai
%A Bhattacharya, Arnab
%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 bhattacharyya-etal-2025-findings
%X This overview paper presents the findings of the two shared tasks organized as part of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA) co-located with IJCNLP-AACL 2025. The shared tasks are: (1) Indic Grammar Error Correction (IndicGEC) and (2) Indic Word Grouping (IndicWG). For GEC, participants were tasked with producing grammatically correct sentences based on given input sentences in five Indian languages. For WG, participants were required to generate a word-grouped variant of a provided sentence in Hindi. The evaluation metric used for GEC was GLEU, while Exact Matching was employed for WG. A total of 14 teams participated in the final phase of the Shared Task 1; 2 teams participated in the final phase of Shared Task 2. The maximum GLEU scores obtained for Hindi, Bangla, Telugu, Tamil and Malayalam languages are respectively 85.69, 95.79, 88.17, 91.57 and 96.02 for the IndicGEC shared task. The highest exact matching score obtained for IndicWG shared task is 45.13%.
%U https://aclanthology.org/2025.bhasha-1.12/
%P 127-134
Markdown (Informal)
[Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025](https://aclanthology.org/2025.bhasha-1.12/) (Bhattacharyya et al., BHASHA 2025)
ACL
- Pramit Bhattacharyya, Karthika N J, Hrishikesh Terdalkar, Manoj Balaji Jagadeeshan, Shubham Kumar Nigam, Arvapalli Sai Susmitha, and Arnab Bhattacharya. 2025. Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025. In Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025), pages 127–134, Mumbai, India. Association for Computational Linguistics.