<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolavi-etal-2025-nayana">
    <titleInfo>
        <title>Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adithya</namePart>
        <namePart type="family">Kolavi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samarth</namePart>
        <namePart type="family">P</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vyoman</namePart>
        <namePart type="family">Jain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sang</namePart>
            <namePart type="family">Truong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rifki</namePart>
            <namePart type="given">Afina</namePart>
            <namePart type="family">Putri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Duc</namePart>
            <namePart type="family">Nguyen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angelina</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Ho</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alice</namePart>
            <namePart type="family">Oh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sanmi</namePart>
            <namePart type="family">Koyejo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-242-8</identifier>
    </relatedItem>
    <abstract>We introduce Nayana, a scalable and efficient framework for adapting Vision-Language Models (VLMs) to low-resource languages. Despite significant advances, modern VLMs remain constrained by the scarcity of training data in non-English languages, limiting their global applicability. Our framework addresses this fundamental challenge through a novel layout-aware synthetic data generation pipeline combined with parameter-efficient adaptation techniques. Instead of requiring extensive manually annotated datasets, Nayana enables existing models to learn new languages effectively using purely synthetic data. Using Low-Rank Adaptation (LoRA), we demonstrate this capability across ten Indic languages: Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu. Through extensive experiments in OCR tasks, we show that models can achieve strong performance in new languages without the traditional requirements of large-scale annotated datasets or extensive model modifications. Nayana’s success in adapting VLMs to new languages with synthetic data establishes a practical pathway for extending AI capabilities to underserved languages, particularly in scenarios where annotated data is scarce or unavailable.</abstract>
    <identifier type="citekey">kolavi-etal-2025-nayana</identifier>
    <identifier type="doi">10.18653/v1/2025.lm4uc-1.11</identifier>
    <location>
        <url>https://aclanthology.org/2025.lm4uc-1.11/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>86</start>
            <end>103</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages
%A Kolavi, Adithya
%A P, Samarth
%A Jain, Vyoman
%Y Truong, Sang
%Y Putri, Rifki Afina
%Y Nguyen, Duc
%Y Wang, Angelina
%Y Ho, Daniel
%Y Oh, Alice
%Y Koyejo, Sanmi
%S Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-242-8
%F kolavi-etal-2025-nayana
%X We introduce Nayana, a scalable and efficient framework for adapting Vision-Language Models (VLMs) to low-resource languages. Despite significant advances, modern VLMs remain constrained by the scarcity of training data in non-English languages, limiting their global applicability. Our framework addresses this fundamental challenge through a novel layout-aware synthetic data generation pipeline combined with parameter-efficient adaptation techniques. Instead of requiring extensive manually annotated datasets, Nayana enables existing models to learn new languages effectively using purely synthetic data. Using Low-Rank Adaptation (LoRA), we demonstrate this capability across ten Indic languages: Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu. Through extensive experiments in OCR tasks, we show that models can achieve strong performance in new languages without the traditional requirements of large-scale annotated datasets or extensive model modifications. Nayana’s success in adapting VLMs to new languages with synthetic data establishes a practical pathway for extending AI capabilities to underserved languages, particularly in scenarios where annotated data is scarce or unavailable.
%R 10.18653/v1/2025.lm4uc-1.11
%U https://aclanthology.org/2025.lm4uc-1.11/
%U https://doi.org/10.18653/v1/2025.lm4uc-1.11
%P 86-103

Markdown (Informal)

[Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages](https://aclanthology.org/2025.lm4uc-1.11/) (Kolavi et al., LM4UC 2025)

• Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages (Kolavi et al., LM4UC 2025)

ACL

• Adithya Kolavi, Samarth P, and Vyoman Jain. 2025. Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages. In Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025), pages 86–103, Albuquerque, New Mexico. Association for Computational Linguistics.