@inproceedings{reynaert-2008-errors,
title = "All, and only, the Errors: more Complete and Consistent Spelling and {OCR}-Error Correction Evaluation",
author = "Reynaert, Martin",
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/477_paper.pdf",
abstract = "Some time in the future, some spelling error correction system will correct all the errors, and only the errors. We need evaluation metrics that will tell us when this has been achieved and that can help guide us there. We survey the current practice in the form of the evaluation scheme of the latest major publication on spelling correction in a leading journal. We are forced to conclude that while the metric used there can tell us exactly when the ultimate goal of spelling correction research has been achieved, it offers little in the way of directions to be followed to eventually get there. We propose to consistently use the well-known metrics Recall and Precision, as combined in the F score, on 5 possible levels of measurement that should guide us more informedly along that path. We describe briefly what is then measured or measurable at these levels and propose a framework that should allow for concisely stating what it is one performs in ones evaluations. We finally contrast our preferred metrics to Accuracy, which is widely used in this field to this day and to the Area-Under-the-Curve, which is increasingly finding acceptance in other fields.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reynaert-2008-errors">
<titleInfo>
<title>All, and only, the Errors: more Complete and Consistent Spelling and OCR-Error Correction Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Reynaert</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>Some time in the future, some spelling error correction system will correct all the errors, and only the errors. We need evaluation metrics that will tell us when this has been achieved and that can help guide us there. We survey the current practice in the form of the evaluation scheme of the latest major publication on spelling correction in a leading journal. We are forced to conclude that while the metric used there can tell us exactly when the ultimate goal of spelling correction research has been achieved, it offers little in the way of directions to be followed to eventually get there. We propose to consistently use the well-known metrics Recall and Precision, as combined in the F score, on 5 possible levels of measurement that should guide us more informedly along that path. We describe briefly what is then measured or measurable at these levels and propose a framework that should allow for concisely stating what it is one performs in ones evaluations. We finally contrast our preferred metrics to Accuracy, which is widely used in this field to this day and to the Area-Under-the-Curve, which is increasingly finding acceptance in other fields.</abstract>
<identifier type="citekey">reynaert-2008-errors</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/477_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All, and only, the Errors: more Complete and Consistent Spelling and OCR-Error Correction Evaluation
%A Reynaert, Martin
%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 reynaert-2008-errors
%X Some time in the future, some spelling error correction system will correct all the errors, and only the errors. We need evaluation metrics that will tell us when this has been achieved and that can help guide us there. We survey the current practice in the form of the evaluation scheme of the latest major publication on spelling correction in a leading journal. We are forced to conclude that while the metric used there can tell us exactly when the ultimate goal of spelling correction research has been achieved, it offers little in the way of directions to be followed to eventually get there. We propose to consistently use the well-known metrics Recall and Precision, as combined in the F score, on 5 possible levels of measurement that should guide us more informedly along that path. We describe briefly what is then measured or measurable at these levels and propose a framework that should allow for concisely stating what it is one performs in ones evaluations. We finally contrast our preferred metrics to Accuracy, which is widely used in this field to this day and to the Area-Under-the-Curve, which is increasingly finding acceptance in other fields.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/477_paper.pdf
Markdown (Informal)
[All, and only, the Errors: more Complete and Consistent Spelling and OCR-Error Correction Evaluation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/477_paper.pdf) (Reynaert, LREC 2008)
ACL