@inproceedings{duong-etal-2021-unsupervised,
title = "An Unsupervised method for {OCR} Post-Correction and Spelling Normalisation for {F}innish",
author = {Duong, Quan and
H{\"a}m{\"a}l{\"a}inen, Mika and
Hengchen, Simon},
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.24",
pages = "240--248",
abstract = "Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We build on previous work on fully automatic unsupervised extraction of parallel data to train a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction designed for English, and adapt it to Finnish by proposing solutions that take the rich morphology of the language into account. Our new method shows increased performance while remaining fully unsupervised, with the added benefit of spelling normalisation. The source code and models are available on GitHub and Zenodo.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duong-etal-2021-unsupervised">
<titleInfo>
<title>An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Duong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hengchen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We build on previous work on fully automatic unsupervised extraction of parallel data to train a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction designed for English, and adapt it to Finnish by proposing solutions that take the rich morphology of the language into account. Our new method shows increased performance while remaining fully unsupervised, with the added benefit of spelling normalisation. The source code and models are available on GitHub and Zenodo.</abstract>
<identifier type="citekey">duong-etal-2021-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.24</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>240</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish
%A Duong, Quan
%A Hämäläinen, Mika
%A Hengchen, Simon
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F duong-etal-2021-unsupervised
%X Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We build on previous work on fully automatic unsupervised extraction of parallel data to train a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction designed for English, and adapt it to Finnish by proposing solutions that take the rich morphology of the language into account. Our new method shows increased performance while remaining fully unsupervised, with the added benefit of spelling normalisation. The source code and models are available on GitHub and Zenodo.
%U https://aclanthology.org/2021.nodalida-main.24
%P 240-248
Markdown (Informal)
[An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish](https://aclanthology.org/2021.nodalida-main.24) (Duong et al., NoDaLiDa 2021)
ACL