@inproceedings{gupta-etal-2021-unsupervised-multi,
title = "Unsupervised Multi-View Post-{OCR} Error Correction With Language Models",
author = "Gupta, Harsh and
Del Corro, Luciano and
Broscheit, Samuel and
Hoffart, Johannes and
Brenner, Eliot",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.680",
doi = "10.18653/v1/2021.emnlp-main.680",
pages = "8647--8652",
abstract = "We investigate post-OCR correction in a setting where we have access to different OCR views of the same document. The goal of this study is to understand if a pretrained language model (LM) can be used in an unsupervised way to reconcile the different OCR views such that their combination contains fewer errors than each individual view. This approach is motivated by scenarios in which unconstrained text generation for error correction is too risky. We evaluated different pretrained LMs on two datasets and found significant gains in realistic scenarios with up to 15{\%} WER improvement over the best OCR view. We also show the importance of domain adaptation for post-OCR correction on out-of-domain documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2021-unsupervised-multi">
<titleInfo>
<title>Unsupervised Multi-View Post-OCR Error Correction With Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciano</namePart>
<namePart type="family">Del Corro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Broscheit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Hoffart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliot</namePart>
<namePart type="family">Brenner</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 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate post-OCR correction in a setting where we have access to different OCR views of the same document. The goal of this study is to understand if a pretrained language model (LM) can be used in an unsupervised way to reconcile the different OCR views such that their combination contains fewer errors than each individual view. This approach is motivated by scenarios in which unconstrained text generation for error correction is too risky. We evaluated different pretrained LMs on two datasets and found significant gains in realistic scenarios with up to 15% WER improvement over the best OCR view. We also show the importance of domain adaptation for post-OCR correction on out-of-domain documents.</abstract>
<identifier type="citekey">gupta-etal-2021-unsupervised-multi</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.680</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.680</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8647</start>
<end>8652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Multi-View Post-OCR Error Correction With Language Models
%A Gupta, Harsh
%A Del Corro, Luciano
%A Broscheit, Samuel
%A Hoffart, Johannes
%A Brenner, Eliot
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F gupta-etal-2021-unsupervised-multi
%X We investigate post-OCR correction in a setting where we have access to different OCR views of the same document. The goal of this study is to understand if a pretrained language model (LM) can be used in an unsupervised way to reconcile the different OCR views such that their combination contains fewer errors than each individual view. This approach is motivated by scenarios in which unconstrained text generation for error correction is too risky. We evaluated different pretrained LMs on two datasets and found significant gains in realistic scenarios with up to 15% WER improvement over the best OCR view. We also show the importance of domain adaptation for post-OCR correction on out-of-domain documents.
%R 10.18653/v1/2021.emnlp-main.680
%U https://aclanthology.org/2021.emnlp-main.680
%U https://doi.org/10.18653/v1/2021.emnlp-main.680
%P 8647-8652
Markdown (Informal)
[Unsupervised Multi-View Post-OCR Error Correction With Language Models](https://aclanthology.org/2021.emnlp-main.680) (Gupta et al., EMNLP 2021)
ACL
- Harsh Gupta, Luciano Del Corro, Samuel Broscheit, Johannes Hoffart, and Eliot Brenner. 2021. Unsupervised Multi-View Post-OCR Error Correction With Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8647–8652, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.