@inproceedings{dobariya-etal-2025-smruti,
title = "Smruti: Grammatical Error Correction for {G}ujarati using {LLM}s with Non-Parametric Memory",
author = "Dobariya, Vrund and
Baxi, Jatayu and
Gambhava, Bhavika and
Bhatt, Brijesh",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.28/",
pages = "473--485",
ISBN = "979-8-89176-303-6",
abstract = "Grammatical Error Correction (GEC) is a fundamental task in Natural Language Processing that focuses on automatically detecting and correcting grammatical errors in text. In this paper, we present a novel approach for GEC for Gujarati. Gujarati is an Indian language spoken by over 55 million people worldwide. Our approach combines a large language model with non-parametric memory modules to address the low-resource challenge. We have evaluated our system on human-annotated and synthetic datasets. The overall result indicates promising results for Gujarati. The proposed approach is generic enough to be adopted by other languages. Furthermore, we release a publicly available evaluation dataset for Gujarati GEC along with an adapted version of the ERRANT framework to enable error-type-wise evaluation in Gujarati."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobariya-etal-2025-smruti">
<titleInfo>
<title>Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vrund</namePart>
<namePart type="family">Dobariya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatayu</namePart>
<namePart type="family">Baxi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavika</namePart>
<namePart type="family">Gambhava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brijesh</namePart>
<namePart type="family">Bhatt</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 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Grammatical Error Correction (GEC) is a fundamental task in Natural Language Processing that focuses on automatically detecting and correcting grammatical errors in text. In this paper, we present a novel approach for GEC for Gujarati. Gujarati is an Indian language spoken by over 55 million people worldwide. Our approach combines a large language model with non-parametric memory modules to address the low-resource challenge. We have evaluated our system on human-annotated and synthetic datasets. The overall result indicates promising results for Gujarati. The proposed approach is generic enough to be adopted by other languages. Furthermore, we release a publicly available evaluation dataset for Gujarati GEC along with an adapted version of the ERRANT framework to enable error-type-wise evaluation in Gujarati.</abstract>
<identifier type="citekey">dobariya-etal-2025-smruti</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.28/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>473</start>
<end>485</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory
%A Dobariya, Vrund
%A Baxi, Jatayu
%A Gambhava, Bhavika
%A Bhatt, Brijesh
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F dobariya-etal-2025-smruti
%X Grammatical Error Correction (GEC) is a fundamental task in Natural Language Processing that focuses on automatically detecting and correcting grammatical errors in text. In this paper, we present a novel approach for GEC for Gujarati. Gujarati is an Indian language spoken by over 55 million people worldwide. Our approach combines a large language model with non-parametric memory modules to address the low-resource challenge. We have evaluated our system on human-annotated and synthetic datasets. The overall result indicates promising results for Gujarati. The proposed approach is generic enough to be adopted by other languages. Furthermore, we release a publicly available evaluation dataset for Gujarati GEC along with an adapted version of the ERRANT framework to enable error-type-wise evaluation in Gujarati.
%U https://aclanthology.org/2025.findings-ijcnlp.28/
%P 473-485
Markdown (Informal)
[Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory](https://aclanthology.org/2025.findings-ijcnlp.28/) (Dobariya et al., Findings 2025)
ACL
- Vrund Dobariya, Jatayu Baxi, Bhavika Gambhava, and Brijesh Bhatt. 2025. Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 473–485, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.