@inproceedings{neveditsin-etal-2026-compact,
title = "Compact Multimodal Language Models as Robust {OCR} Alternatives for Noisy Textual Clinical Reports",
author = "Neveditsin, Nikita and
Lingras, Pawan and
Patil, Salil and
Patil, Swarup and
Mago, Vijay Kumar",
editor = {Matusevych, Yevgen and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en and
Aletras, Nikolaos},
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-industry.4/",
pages = "48--59",
ISBN = "979-8-89176-384-5",
abstract = "Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neveditsin-etal-2026-compact">
<titleInfo>
<title>Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Neveditsin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Lingras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salil</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swarup</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Mago</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgen</namePart>
<namePart type="family">Matusevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-384-5</identifier>
</relatedItem>
<abstract>Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization.</abstract>
<identifier type="citekey">neveditsin-etal-2026-compact</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-industry.4/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>48</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports
%A Neveditsin, Nikita
%A Lingras, Pawan
%A Patil, Salil
%A Patil, Swarup
%A Mago, Vijay Kumar
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F neveditsin-etal-2026-compact
%X Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization.
%U https://aclanthology.org/2026.eacl-industry.4/
%P 48-59
Markdown (Informal)
[Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports](https://aclanthology.org/2026.eacl-industry.4/) (Neveditsin et al., EACL 2026)
ACL