@inproceedings{michail-etal-2025-cheap,
title = "Cheap Character Noise for {OCR}-Robust Multilingual Embeddings",
author = "Michail, Andrianos and
Opitz, Juri and
Wang, Yining and
Meister, Robin and
Sennrich, Rico and
Clematide, Simon",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.609/",
doi = "10.18653/v1/2025.findings-acl.609",
pages = "11705--11716",
ISBN = "979-8-89176-256-5",
abstract = "The large amount of text collections digitized by imperfect OCR systems requires semantic search models that perform robustly on noisy input. Such collections are highly heterogeneous, with varying degrees of OCR quality, spelling conventions and other inconsistencies {---}all phenomena that are underrepresented in the training data of standard embedding models, with ramifications for their generalization. In our paper, we show that this problem can be alleviated with a simple and inexpensive method that does not require supervision or in-domain training. Specifically, we fine-tune existing multilingual models using noisy texts and a contrastive loss. We show that these models show considerable improvements across different noise conditions. Control experiments indicate minimal, and occasionally positive, impact on standard similarity tasks. These findings suggest that embedding models can be inexpensively adapted for cross-lingual semantic search in heterogeneous, digitized corpora. We publicly release our code, datasets, and models at https://github.com/impresso/ocr-robust-multilingual-embeddings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michail-etal-2025-cheap">
<titleInfo>
<title>Cheap Character Noise for OCR-Robust Multilingual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrianos</namePart>
<namePart type="family">Michail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yining</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Meister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>The large amount of text collections digitized by imperfect OCR systems requires semantic search models that perform robustly on noisy input. Such collections are highly heterogeneous, with varying degrees of OCR quality, spelling conventions and other inconsistencies —all phenomena that are underrepresented in the training data of standard embedding models, with ramifications for their generalization. In our paper, we show that this problem can be alleviated with a simple and inexpensive method that does not require supervision or in-domain training. Specifically, we fine-tune existing multilingual models using noisy texts and a contrastive loss. We show that these models show considerable improvements across different noise conditions. Control experiments indicate minimal, and occasionally positive, impact on standard similarity tasks. These findings suggest that embedding models can be inexpensively adapted for cross-lingual semantic search in heterogeneous, digitized corpora. We publicly release our code, datasets, and models at https://github.com/impresso/ocr-robust-multilingual-embeddings.</abstract>
<identifier type="citekey">michail-etal-2025-cheap</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.609</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.609/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>11705</start>
<end>11716</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cheap Character Noise for OCR-Robust Multilingual Embeddings
%A Michail, Andrianos
%A Opitz, Juri
%A Wang, Yining
%A Meister, Robin
%A Sennrich, Rico
%A Clematide, Simon
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F michail-etal-2025-cheap
%X The large amount of text collections digitized by imperfect OCR systems requires semantic search models that perform robustly on noisy input. Such collections are highly heterogeneous, with varying degrees of OCR quality, spelling conventions and other inconsistencies —all phenomena that are underrepresented in the training data of standard embedding models, with ramifications for their generalization. In our paper, we show that this problem can be alleviated with a simple and inexpensive method that does not require supervision or in-domain training. Specifically, we fine-tune existing multilingual models using noisy texts and a contrastive loss. We show that these models show considerable improvements across different noise conditions. Control experiments indicate minimal, and occasionally positive, impact on standard similarity tasks. These findings suggest that embedding models can be inexpensively adapted for cross-lingual semantic search in heterogeneous, digitized corpora. We publicly release our code, datasets, and models at https://github.com/impresso/ocr-robust-multilingual-embeddings.
%R 10.18653/v1/2025.findings-acl.609
%U https://aclanthology.org/2025.findings-acl.609/
%U https://doi.org/10.18653/v1/2025.findings-acl.609
%P 11705-11716
Markdown (Informal)
[Cheap Character Noise for OCR-Robust Multilingual Embeddings](https://aclanthology.org/2025.findings-acl.609/) (Michail et al., Findings 2025)
ACL
- Andrianos Michail, Juri Opitz, Yining Wang, Robin Meister, Rico Sennrich, and Simon Clematide. 2025. Cheap Character Noise for OCR-Robust Multilingual Embeddings. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11705–11716, Vienna, Austria. Association for Computational Linguistics.