@inproceedings{domingo-casacuberta-2018-spelling,
title = "Spelling Normalization of Historical Documents by Using a Machine Translation Approach",
author = "Domingo, Miguel and
Casacuberta, Francisco",
editor = "P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'\i}nez, Felipe and
Espl{\`a}-Gomis, Miquel and
Popovi{\'c}, Maja and
Rico, Celia and
Martins, Andr{\'e} and
Van den Bogaert, Joachim and
Forcada, Mikel L.",
booktitle = "Proceedings of the 21st Annual Conference of the European Association for Machine Translation",
month = may,
year = "2018",
address = "Alicante, Spain",
url = "https://aclanthology.org/2018.eamt-main.13",
pages = "149--158",
abstract = "The lack of a spelling convention in historical documents makes their orthography to change depending on the author and the time period in which each document was written. This represents a problem for the preservation of the cultural heritage, which strives to create a digital text version of a historical document. With the aim of solving this problem, we propose three approaches{---}based on statistical, neural and character-based machine translation{---}to adapt the document{'}s spelling to modern standards. We tested these approaches in different scenarios, obtaining very encouraging results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="domingo-casacuberta-2018-spelling">
<titleInfo>
<title>Spelling Normalization of Historical Documents by Using a Machine Translation Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Domingo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Casacuberta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celia</namePart>
<namePart type="family">Rico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Alicante, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The lack of a spelling convention in historical documents makes their orthography to change depending on the author and the time period in which each document was written. This represents a problem for the preservation of the cultural heritage, which strives to create a digital text version of a historical document. With the aim of solving this problem, we propose three approaches—based on statistical, neural and character-based machine translation—to adapt the document’s spelling to modern standards. We tested these approaches in different scenarios, obtaining very encouraging results.</abstract>
<identifier type="citekey">domingo-casacuberta-2018-spelling</identifier>
<location>
<url>https://aclanthology.org/2018.eamt-main.13</url>
</location>
<part>
<date>2018-05</date>
<extent unit="page">
<start>149</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spelling Normalization of Historical Documents by Using a Machine Translation Approach
%A Domingo, Miguel
%A Casacuberta, Francisco
%Y Pérez-Ortiz, Juan Antonio
%Y Sánchez-Martínez, Felipe
%Y Esplà-Gomis, Miquel
%Y Popović, Maja
%Y Rico, Celia
%Y Martins, André
%Y Van den Bogaert, Joachim
%Y Forcada, Mikel L.
%S Proceedings of the 21st Annual Conference of the European Association for Machine Translation
%D 2018
%8 May
%C Alicante, Spain
%F domingo-casacuberta-2018-spelling
%X The lack of a spelling convention in historical documents makes their orthography to change depending on the author and the time period in which each document was written. This represents a problem for the preservation of the cultural heritage, which strives to create a digital text version of a historical document. With the aim of solving this problem, we propose three approaches—based on statistical, neural and character-based machine translation—to adapt the document’s spelling to modern standards. We tested these approaches in different scenarios, obtaining very encouraging results.
%U https://aclanthology.org/2018.eamt-main.13
%P 149-158
Markdown (Informal)
[Spelling Normalization of Historical Documents by Using a Machine Translation Approach](https://aclanthology.org/2018.eamt-main.13) (Domingo & Casacuberta, EAMT 2018)
ACL