@inproceedings{soper-etal-2021-bart,
title = "{BART} for Post-Correction of {OCR} Newspaper Text",
author = "Soper, Elizabeth and
Fujimoto, Stanley and
Yu, Yen-Yun",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wnut-1.31",
doi = "10.18653/v1/2021.wnut-1.31",
pages = "284--290",
abstract = "Optical character recognition (OCR) from newspaper page images is susceptible to noise due to degradation of old documents and variation in typesetting. In this report, we present a novel approach to OCR post-correction. We cast error correction as a translation task, and fine-tune BART, a transformer-based sequence-to-sequence language model pretrained to denoise corrupted text. We are the first to use sentence-level transformer models for OCR post-correction, and our best model achieves a 29.4{\%} improvement in character accuracy over the original noisy OCR text. Our results demonstrate the utility of pretrained language models for dealing with noisy text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soper-etal-2021-bart">
<titleInfo>
<title>BART for Post-Correction of OCR Newspaper Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Soper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stanley</namePart>
<namePart type="family">Fujimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen-Yun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Optical character recognition (OCR) from newspaper page images is susceptible to noise due to degradation of old documents and variation in typesetting. In this report, we present a novel approach to OCR post-correction. We cast error correction as a translation task, and fine-tune BART, a transformer-based sequence-to-sequence language model pretrained to denoise corrupted text. We are the first to use sentence-level transformer models for OCR post-correction, and our best model achieves a 29.4% improvement in character accuracy over the original noisy OCR text. Our results demonstrate the utility of pretrained language models for dealing with noisy text.</abstract>
<identifier type="citekey">soper-etal-2021-bart</identifier>
<identifier type="doi">10.18653/v1/2021.wnut-1.31</identifier>
<location>
<url>https://aclanthology.org/2021.wnut-1.31</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>284</start>
<end>290</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BART for Post-Correction of OCR Newspaper Text
%A Soper, Elizabeth
%A Fujimoto, Stanley
%A Yu, Yen-Yun
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F soper-etal-2021-bart
%X Optical character recognition (OCR) from newspaper page images is susceptible to noise due to degradation of old documents and variation in typesetting. In this report, we present a novel approach to OCR post-correction. We cast error correction as a translation task, and fine-tune BART, a transformer-based sequence-to-sequence language model pretrained to denoise corrupted text. We are the first to use sentence-level transformer models for OCR post-correction, and our best model achieves a 29.4% improvement in character accuracy over the original noisy OCR text. Our results demonstrate the utility of pretrained language models for dealing with noisy text.
%R 10.18653/v1/2021.wnut-1.31
%U https://aclanthology.org/2021.wnut-1.31
%U https://doi.org/10.18653/v1/2021.wnut-1.31
%P 284-290
Markdown (Informal)
[BART for Post-Correction of OCR Newspaper Text](https://aclanthology.org/2021.wnut-1.31) (Soper et al., WNUT 2021)
ACL
- Elizabeth Soper, Stanley Fujimoto, and Yen-Yun Yu. 2021. BART for Post-Correction of OCR Newspaper Text. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 284–290, Online. Association for Computational Linguistics.