@inproceedings{han-etal-2010-using,
title = "Using an Error-Annotated Learner Corpus to Develop an {ESL}/{EFL} Error Correction System",
author = "Han, Na-Rae and
Tetreault, Joel and
Lee, Soo-Hwa and
Ha, Jin-Young",
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/821_Paper.pdf",
abstract = "This paper presents research on building a model of grammatical error correction, for preposition errors in particular, in English text produced by language learners. Unlike most previous work which trains a statistical classifier exclusively on well-formed text written by native speakers, we train a classifier on a large-scale, error-tagged corpus of English essays written by ESL learners, relying on contextual and grammatical features surrounding preposition usage. First, we show that such a model can achieve high performance values: 93.3{\%} precision and 14.8{\%} recall for error detection and 81.7{\%} precision and 13.2{\%} recall for error detection and correction when tested on preposition replacement errors. Second, we show that this model outperforms models trained on well-edited text produced by native speakers of English. We discuss the implications of our approach in the area of language error modeling and the issues stemming from working with a noisy data set whose error annotations are not exhaustive.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2010-using">
<titleInfo>
<title>Using an Error-Annotated Learner Corpus to Develop an ESL/EFL Error Correction System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Na-Rae</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soo-Hwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Young</namePart>
<namePart type="family">Ha</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>This paper presents research on building a model of grammatical error correction, for preposition errors in particular, in English text produced by language learners. Unlike most previous work which trains a statistical classifier exclusively on well-formed text written by native speakers, we train a classifier on a large-scale, error-tagged corpus of English essays written by ESL learners, relying on contextual and grammatical features surrounding preposition usage. First, we show that such a model can achieve high performance values: 93.3% precision and 14.8% recall for error detection and 81.7% precision and 13.2% recall for error detection and correction when tested on preposition replacement errors. Second, we show that this model outperforms models trained on well-edited text produced by native speakers of English. We discuss the implications of our approach in the area of language error modeling and the issues stemming from working with a noisy data set whose error annotations are not exhaustive.</abstract>
<identifier type="citekey">han-etal-2010-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/821_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using an Error-Annotated Learner Corpus to Develop an ESL/EFL Error Correction System
%A Han, Na-Rae
%A Tetreault, Joel
%A Lee, Soo-Hwa
%A Ha, Jin-Young
%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 han-etal-2010-using
%X This paper presents research on building a model of grammatical error correction, for preposition errors in particular, in English text produced by language learners. Unlike most previous work which trains a statistical classifier exclusively on well-formed text written by native speakers, we train a classifier on a large-scale, error-tagged corpus of English essays written by ESL learners, relying on contextual and grammatical features surrounding preposition usage. First, we show that such a model can achieve high performance values: 93.3% precision and 14.8% recall for error detection and 81.7% precision and 13.2% recall for error detection and correction when tested on preposition replacement errors. Second, we show that this model outperforms models trained on well-edited text produced by native speakers of English. We discuss the implications of our approach in the area of language error modeling and the issues stemming from working with a noisy data set whose error annotations are not exhaustive.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/821_Paper.pdf
Markdown (Informal)
[Using an Error-Annotated Learner Corpus to Develop an ESL/EFL Error Correction System](http://www.lrec-conf.org/proceedings/lrec2010/pdf/821_Paper.pdf) (Han et al., LREC 2010)
ACL