@inproceedings{hermet-etal-2008-using,
title = "Using the Web as a Linguistic Resource to Automatically Correct Lexico-Syntactic Errors",
author = "Hermet, Matthieu and
D{\'e}silets, Alain and
Szpakowicz, Stan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/220_paper.pdf",
abstract = "This paper presents an algorithm for correcting language errors typical of second-language learners. We focus on preposition errors, which are very common among second-language learners but are not addressed well by current commercial grammar correctors and editing aids. The algorithm takes as input a sentence containing a preposition error (and possibly other errors as well), and outputs the correct preposition for that particular sentence context. We use a two-phase hybrid rule-based and statistical approach. In the first phase, rule-based processing is used to generate a short expression that captures the context of use of the preposition in the input sentence. In the second phase, Web searches are used to evaluate the frequency of this expression, when alternative prepositions are used instead of the original one. We tested this algorithm on a corpus of 133 French sentences written by intermediate second-language learners, and found that it could address 69.9{\%} of those cases. In contrast, we found that the best French grammar and spell checker currently on the market, Antidote, addressed only 3{\%} of those cases. We also showed that performance degrades gracefully when using a corpus of frequent n-grams to evaluate frequencies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hermet-etal-2008-using">
<titleInfo>
<title>Using the Web as a Linguistic Resource to Automatically Correct Lexico-Syntactic Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthieu</namePart>
<namePart type="family">Hermet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alain</namePart>
<namePart type="family">Désilets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an algorithm for correcting language errors typical of second-language learners. We focus on preposition errors, which are very common among second-language learners but are not addressed well by current commercial grammar correctors and editing aids. The algorithm takes as input a sentence containing a preposition error (and possibly other errors as well), and outputs the correct preposition for that particular sentence context. We use a two-phase hybrid rule-based and statistical approach. In the first phase, rule-based processing is used to generate a short expression that captures the context of use of the preposition in the input sentence. In the second phase, Web searches are used to evaluate the frequency of this expression, when alternative prepositions are used instead of the original one. We tested this algorithm on a corpus of 133 French sentences written by intermediate second-language learners, and found that it could address 69.9% of those cases. In contrast, we found that the best French grammar and spell checker currently on the market, Antidote, addressed only 3% of those cases. We also showed that performance degrades gracefully when using a corpus of frequent n-grams to evaluate frequencies.</abstract>
<identifier type="citekey">hermet-etal-2008-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/220_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using the Web as a Linguistic Resource to Automatically Correct Lexico-Syntactic Errors
%A Hermet, Matthieu
%A Désilets, Alain
%A Szpakowicz, Stan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F hermet-etal-2008-using
%X This paper presents an algorithm for correcting language errors typical of second-language learners. We focus on preposition errors, which are very common among second-language learners but are not addressed well by current commercial grammar correctors and editing aids. The algorithm takes as input a sentence containing a preposition error (and possibly other errors as well), and outputs the correct preposition for that particular sentence context. We use a two-phase hybrid rule-based and statistical approach. In the first phase, rule-based processing is used to generate a short expression that captures the context of use of the preposition in the input sentence. In the second phase, Web searches are used to evaluate the frequency of this expression, when alternative prepositions are used instead of the original one. We tested this algorithm on a corpus of 133 French sentences written by intermediate second-language learners, and found that it could address 69.9% of those cases. In contrast, we found that the best French grammar and spell checker currently on the market, Antidote, addressed only 3% of those cases. We also showed that performance degrades gracefully when using a corpus of frequent n-grams to evaluate frequencies.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/220_paper.pdf
Markdown (Informal)
[Using the Web as a Linguistic Resource to Automatically Correct Lexico-Syntactic Errors](http://www.lrec-conf.org/proceedings/lrec2008/pdf/220_paper.pdf) (Hermet et al., LREC 2008)
ACL