@inproceedings{almeida-etal-2010-bigorna,
title = "Bigorna {--} A Toolkit for Orthography Migration Challenges",
author = "Almeida, Jos{\'e} Jo{\~a}o and
Santos, Andr{\'e} and
Sim{\~o}es, Alberto",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/898_Paper.pdf",
abstract = "Languages are born, evolve and, eventually, die. During this evolution their spelling rules (and sometimes the syntactic and semantic ones) change, putting old documents out of use. In Portugal, a pair of political agreements with Brazil forced relevant changes on the way the Portuguese language is written. In this article we will detail these two Orthographic Agreements (one in the thirties and the other more recently, in the nineties), and the challenges present on the automatic migration of old documents spelling to their actual one. We will reveal Bigorna, a toolkit for the classification of language variants, their comparison and the conversion of texts in different language versions. These tools will be explained together with examples of migration issues. As Birgorna relies on a set of conversion rules we will also discuss how to infer conversion rules from a set of documents (texts with different ages). The document concludes with a brief evaluation on the conversion and classification tool results and their relevance in the current Portuguese language scenario.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almeida-etal-2010-bigorna">
<titleInfo>
<title>Bigorna – A Toolkit for Orthography Migration Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">João</namePart>
<namePart type="family">Almeida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Simões</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Languages are born, evolve and, eventually, die. During this evolution their spelling rules (and sometimes the syntactic and semantic ones) change, putting old documents out of use. In Portugal, a pair of political agreements with Brazil forced relevant changes on the way the Portuguese language is written. In this article we will detail these two Orthographic Agreements (one in the thirties and the other more recently, in the nineties), and the challenges present on the automatic migration of old documents spelling to their actual one. We will reveal Bigorna, a toolkit for the classification of language variants, their comparison and the conversion of texts in different language versions. These tools will be explained together with examples of migration issues. As Birgorna relies on a set of conversion rules we will also discuss how to infer conversion rules from a set of documents (texts with different ages). The document concludes with a brief evaluation on the conversion and classification tool results and their relevance in the current Portuguese language scenario.</abstract>
<identifier type="citekey">almeida-etal-2010-bigorna</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/898_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bigorna – A Toolkit for Orthography Migration Challenges
%A Almeida, José João
%A Santos, André
%A Simões, Alberto
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F almeida-etal-2010-bigorna
%X Languages are born, evolve and, eventually, die. During this evolution their spelling rules (and sometimes the syntactic and semantic ones) change, putting old documents out of use. In Portugal, a pair of political agreements with Brazil forced relevant changes on the way the Portuguese language is written. In this article we will detail these two Orthographic Agreements (one in the thirties and the other more recently, in the nineties), and the challenges present on the automatic migration of old documents spelling to their actual one. We will reveal Bigorna, a toolkit for the classification of language variants, their comparison and the conversion of texts in different language versions. These tools will be explained together with examples of migration issues. As Birgorna relies on a set of conversion rules we will also discuss how to infer conversion rules from a set of documents (texts with different ages). The document concludes with a brief evaluation on the conversion and classification tool results and their relevance in the current Portuguese language scenario.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/898_Paper.pdf
Markdown (Informal)
[Bigorna – A Toolkit for Orthography Migration Challenges](http://www.lrec-conf.org/proceedings/lrec2010/pdf/898_Paper.pdf) (Almeida et al., LREC 2010)
ACL
- José João Almeida, André Santos, and Alberto Simões. 2010. Bigorna – A Toolkit for Orthography Migration Challenges. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).