@inproceedings{hamalainen-hengchen-2019-paft,
title = "From the Paft to the Fiiture: a Fully Automatic {NMT} and Word Embeddings Method for {OCR} Post-Correction",
author = {H{\"a}m{\"a}l{\"a}inen, Mika and
Hengchen, Simon},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1051",
doi = "10.26615/978-954-452-056-4_051",
pages = "431--436",
abstract = "A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process. 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 present a fully automatic unsupervised way of extracting parallel data for training a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamalainen-hengchen-2019-paft">
<titleInfo>
<title>From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction</title>
</titleInfo>
<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>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process. 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 present a fully automatic unsupervised way of extracting parallel data for training a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction.</abstract>
<identifier type="citekey">hamalainen-hengchen-2019-paft</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_051</identifier>
<location>
<url>https://aclanthology.org/R19-1051</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>431</start>
<end>436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction
%A Hämäläinen, Mika
%A Hengchen, Simon
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F hamalainen-hengchen-2019-paft
%X A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process. 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 present a fully automatic unsupervised way of extracting parallel data for training a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction.
%R 10.26615/978-954-452-056-4_051
%U https://aclanthology.org/R19-1051
%U https://doi.org/10.26615/978-954-452-056-4_051
%P 431-436
Markdown (Informal)
[From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction](https://aclanthology.org/R19-1051) (Hämäläinen & Hengchen, RANLP 2019)
ACL