@inproceedings{ramesh-rajalakshmi-2025-dlrg,
title = "{DLRG} at {BHASHA}: Task 1 ({I}ndic{GEC}): A Hybrid Neurosymbolic Approach for {T}amil and {M}alayalam Grammatical Error Correction",
author = "Ramesh, Akshay and
Rajalakshmi, Ratnavel",
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-1.16/",
pages = "155--163",
ISBN = "979-8-89176-313-5",
abstract = "Grammatical Error Correction (GEC) for low-resource Indic languages remains challenging due to limited annotated data and morphological complexity. We present a hybrid neurosymbolic GEC system that combines neural sequence-to-sequence models with explicit language-specific rule-based pattern matching. Our approach leverages parameter-efficient LoRA adaptation on aggressively augmented data to fine-tune pre-trained mT5 models, followed by learned correction rules through intelligent ensemble strategies. The proposed hybrid architecture achieved 85.34{\%} GLEU for Tamil (Rank 8) and 95.06{\%} GLEU for Malayalam (Rank 2) on the provided IndicGEC test sets, outperforming individual neural and rule-based approaches. The system incorporates conservative safety mechanisms to prevent catastrophic deletions and over-corrections, thus ensuring robustness and real-world applicability. Our work demonstrates that extremely low-resource GEC can be effectively addressed by combining neural generalization with symbolic precision."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramesh-rajalakshmi-2025-dlrg">
<titleInfo>
<title>DLRG at BHASHA: Task 1 (IndicGEC): A Hybrid Neurosymbolic Approach for Tamil and Malayalam Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshay</namePart>
<namePart type="family">Ramesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnavel</namePart>
<namePart type="family">Rajalakshmi</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>Grammatical Error Correction (GEC) for low-resource Indic languages remains challenging due to limited annotated data and morphological complexity. We present a hybrid neurosymbolic GEC system that combines neural sequence-to-sequence models with explicit language-specific rule-based pattern matching. Our approach leverages parameter-efficient LoRA adaptation on aggressively augmented data to fine-tune pre-trained mT5 models, followed by learned correction rules through intelligent ensemble strategies. The proposed hybrid architecture achieved 85.34% GLEU for Tamil (Rank 8) and 95.06% GLEU for Malayalam (Rank 2) on the provided IndicGEC test sets, outperforming individual neural and rule-based approaches. The system incorporates conservative safety mechanisms to prevent catastrophic deletions and over-corrections, thus ensuring robustness and real-world applicability. Our work demonstrates that extremely low-resource GEC can be effectively addressed by combining neural generalization with symbolic precision.</abstract>
<identifier type="citekey">ramesh-rajalakshmi-2025-dlrg</identifier>
<location>
<url>https://aclanthology.org/2025.bhasha-1.16/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>155</start>
<end>163</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DLRG at BHASHA: Task 1 (IndicGEC): A Hybrid Neurosymbolic Approach for Tamil and Malayalam Grammatical Error Correction
%A Ramesh, Akshay
%A Rajalakshmi, Ratnavel
%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 ramesh-rajalakshmi-2025-dlrg
%X Grammatical Error Correction (GEC) for low-resource Indic languages remains challenging due to limited annotated data and morphological complexity. We present a hybrid neurosymbolic GEC system that combines neural sequence-to-sequence models with explicit language-specific rule-based pattern matching. Our approach leverages parameter-efficient LoRA adaptation on aggressively augmented data to fine-tune pre-trained mT5 models, followed by learned correction rules through intelligent ensemble strategies. The proposed hybrid architecture achieved 85.34% GLEU for Tamil (Rank 8) and 95.06% GLEU for Malayalam (Rank 2) on the provided IndicGEC test sets, outperforming individual neural and rule-based approaches. The system incorporates conservative safety mechanisms to prevent catastrophic deletions and over-corrections, thus ensuring robustness and real-world applicability. Our work demonstrates that extremely low-resource GEC can be effectively addressed by combining neural generalization with symbolic precision.
%U https://aclanthology.org/2025.bhasha-1.16/
%P 155-163
Markdown (Informal)
[DLRG at BHASHA: Task 1 (IndicGEC): A Hybrid Neurosymbolic Approach for Tamil and Malayalam Grammatical Error Correction](https://aclanthology.org/2025.bhasha-1.16/) (Ramesh & Rajalakshmi, BHASHA 2025)
ACL