@inproceedings{sepulveda-torres-etal-2014-generating,
title = "Generating a Lexicon of Errors in {P}ortuguese to Support an Error Identification System for {S}panish Native Learners",
author = "Sep{\'u}lveda Torres, Lianet and
Duran, Magali Sanches and
Alu{\'\i}sio, Sandra",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/247_Paper.pdf",
pages = "3952--3957",
abstract = "Portuguese is a less resourced language in what concerns foreign language learning. Aiming to inform a module of a system designed to support scientific written production of Spanish native speakers learning Portuguese, we developed an approach to automatically generate a lexicon of wrong words, reproducing language transfer errors made by such foreign learners. Each item of the artificially generated lexicon contains, besides the wrong word, the respective Spanish and Portuguese correct words. The wrong word is used to identify the interlanguage error and the correct Spanish and Portuguese forms are used to generate the suggestions. Keeping control of the correct word forms, we can provide correction or, at least, useful suggestions for the learners. We propose to combine two automatic procedures to obtain the error correction: i) a similarity measure and ii) a translation algorithm based on aligned parallel corpus. The similarity-based method achieved a precision of 52{\%}, whereas the alignment-based method achieved a precision of 90{\%}. In this paper we focus only on interlanguage errors involving suffixes that have different forms in both languages. The approach, however, is very promising to tackle other types of errors, such as gender errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sepulveda-torres-etal-2014-generating">
<titleInfo>
<title>Generating a Lexicon of Errors in Portuguese to Support an Error Identification System for Spanish Native Learners</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lianet</namePart>
<namePart type="family">Sepúlveda Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magali</namePart>
<namePart type="given">Sanches</namePart>
<namePart type="family">Duran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Aluísio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Portuguese is a less resourced language in what concerns foreign language learning. Aiming to inform a module of a system designed to support scientific written production of Spanish native speakers learning Portuguese, we developed an approach to automatically generate a lexicon of wrong words, reproducing language transfer errors made by such foreign learners. Each item of the artificially generated lexicon contains, besides the wrong word, the respective Spanish and Portuguese correct words. The wrong word is used to identify the interlanguage error and the correct Spanish and Portuguese forms are used to generate the suggestions. Keeping control of the correct word forms, we can provide correction or, at least, useful suggestions for the learners. We propose to combine two automatic procedures to obtain the error correction: i) a similarity measure and ii) a translation algorithm based on aligned parallel corpus. The similarity-based method achieved a precision of 52%, whereas the alignment-based method achieved a precision of 90%. In this paper we focus only on interlanguage errors involving suffixes that have different forms in both languages. The approach, however, is very promising to tackle other types of errors, such as gender errors.</abstract>
<identifier type="citekey">sepulveda-torres-etal-2014-generating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/247_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3952</start>
<end>3957</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating a Lexicon of Errors in Portuguese to Support an Error Identification System for Spanish Native Learners
%A Sepúlveda Torres, Lianet
%A Duran, Magali Sanches
%A Aluísio, Sandra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F sepulveda-torres-etal-2014-generating
%X Portuguese is a less resourced language in what concerns foreign language learning. Aiming to inform a module of a system designed to support scientific written production of Spanish native speakers learning Portuguese, we developed an approach to automatically generate a lexicon of wrong words, reproducing language transfer errors made by such foreign learners. Each item of the artificially generated lexicon contains, besides the wrong word, the respective Spanish and Portuguese correct words. The wrong word is used to identify the interlanguage error and the correct Spanish and Portuguese forms are used to generate the suggestions. Keeping control of the correct word forms, we can provide correction or, at least, useful suggestions for the learners. We propose to combine two automatic procedures to obtain the error correction: i) a similarity measure and ii) a translation algorithm based on aligned parallel corpus. The similarity-based method achieved a precision of 52%, whereas the alignment-based method achieved a precision of 90%. In this paper we focus only on interlanguage errors involving suffixes that have different forms in both languages. The approach, however, is very promising to tackle other types of errors, such as gender errors.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/247_Paper.pdf
%P 3952-3957
Markdown (Informal)
[Generating a Lexicon of Errors in Portuguese to Support an Error Identification System for Spanish Native Learners](http://www.lrec-conf.org/proceedings/lrec2014/pdf/247_Paper.pdf) (Sepúlveda Torres et al., LREC 2014)
ACL