@inproceedings{etxeberria-etal-2016-evaluating,
title = "Evaluating the Noisy Channel Model for the Normalization of Historical Texts: {B}asque, {S}panish and {S}lovene",
author = "Etxeberria, Izaskun and
Alegria, I{\~n}aki and
Uria, Larraitz and
Hulden, Mans",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1169",
pages = "1064--1069",
abstract = "This paper presents a method for the normalization of historical texts using a combination of weighted finite-state transducers and language models. We have extended our previous work on the normalization of dialectal texts and tested the method against a 17th century literary work in Basque. This preprocessed corpus is made available in the LREC repository. The performance of this method for learning relations between historical and contemporary word forms is evaluated against resources in three languages. The method we present learns to map phonological changes using a noisy channel model. The model is based on techniques commonly used for phonological inference and producing Grapheme-to-Grapheme conversion systems encoded as weighted transducers and produces F-scores above 80{\%} in the task for Basque. A wider evaluation shows that the approach performs equally well with all the languages in our evaluation suite: Basque, Spanish and Slovene. A comparison against other methods that address the same task is also provided.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etxeberria-etal-2016-evaluating">
<titleInfo>
<title>Evaluating the Noisy Channel Model for the Normalization of Historical Texts: Basque, Spanish and Slovene</title>
</titleInfo>
<name type="personal">
<namePart type="given">Izaskun</namePart>
<namePart type="family">Etxeberria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">Alegria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larraitz</namePart>
<namePart type="family">Uria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mans</namePart>
<namePart type="family">Hulden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a method for the normalization of historical texts using a combination of weighted finite-state transducers and language models. We have extended our previous work on the normalization of dialectal texts and tested the method against a 17th century literary work in Basque. This preprocessed corpus is made available in the LREC repository. The performance of this method for learning relations between historical and contemporary word forms is evaluated against resources in three languages. The method we present learns to map phonological changes using a noisy channel model. The model is based on techniques commonly used for phonological inference and producing Grapheme-to-Grapheme conversion systems encoded as weighted transducers and produces F-scores above 80% in the task for Basque. A wider evaluation shows that the approach performs equally well with all the languages in our evaluation suite: Basque, Spanish and Slovene. A comparison against other methods that address the same task is also provided.</abstract>
<identifier type="citekey">etxeberria-etal-2016-evaluating</identifier>
<location>
<url>https://aclanthology.org/L16-1169</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1064</start>
<end>1069</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Noisy Channel Model for the Normalization of Historical Texts: Basque, Spanish and Slovene
%A Etxeberria, Izaskun
%A Alegria, Iñaki
%A Uria, Larraitz
%A Hulden, Mans
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F etxeberria-etal-2016-evaluating
%X This paper presents a method for the normalization of historical texts using a combination of weighted finite-state transducers and language models. We have extended our previous work on the normalization of dialectal texts and tested the method against a 17th century literary work in Basque. This preprocessed corpus is made available in the LREC repository. The performance of this method for learning relations between historical and contemporary word forms is evaluated against resources in three languages. The method we present learns to map phonological changes using a noisy channel model. The model is based on techniques commonly used for phonological inference and producing Grapheme-to-Grapheme conversion systems encoded as weighted transducers and produces F-scores above 80% in the task for Basque. A wider evaluation shows that the approach performs equally well with all the languages in our evaluation suite: Basque, Spanish and Slovene. A comparison against other methods that address the same task is also provided.
%U https://aclanthology.org/L16-1169
%P 1064-1069
Markdown (Informal)
[Evaluating the Noisy Channel Model for the Normalization of Historical Texts: Basque, Spanish and Slovene](https://aclanthology.org/L16-1169) (Etxeberria et al., LREC 2016)
ACL