@inproceedings{bick-etal-2024-man,
title = "Man or Machine: Evaluating Spelling Error Detection in {D}anish Newspaper Corpora",
author = "Bick, Eckhard and
Blom, Jonas Nygaard and
Rathje, Marianne and
Schack, J{\o}rgen",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.sigul-1.24",
pages = "204--211",
abstract = "This paper evaluates frequency and detection performance for both spelling and grammatical errors in a corpus of published Danish newspaper texts, comparing the results of three human proofreaders with those of an automatic system, DanProof. Adopting the error categorization scheme of the latter, we look at the accuracy of individual error types and their relative distribution over time, as well as the adequacy of suggested corrections. Finally, we discuss so-called artefact errors introduced by corpus processing, and the potential of DanProof as a corpus cleaning tool for identifying and correcting format conversion, OCR or other compilation errors. In the evaluation, with balanced F1-scores of 77.6 and 67.6 for 1999 texts and 2019 texts, respectively, DanProof achieved a higher recall and accuracy than the individual human annotators, and contributed the largest share of errors not detected by others (16.4{\%} for 1999 and 23.6{\%} for 2019). However, the human annotators had a significantly higher precision. Not counting artifacts, the overall error frequency in the corpus was low ( 0.5{\%}), and less than half in the newer texts compared to the older ones, a change that mostly concerned orthographical errors, with a correspondingly higher relative share of grammatical errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bick-etal-2024-man">
<titleInfo>
<title>Man or Machine: Evaluating Spelling Error Detection in Danish Newspaper Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eckhard</namePart>
<namePart type="family">Bick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="given">Nygaard</namePart>
<namePart type="family">Blom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianne</namePart>
<namePart type="family">Rathje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jørgen</namePart>
<namePart type="family">Schack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper evaluates frequency and detection performance for both spelling and grammatical errors in a corpus of published Danish newspaper texts, comparing the results of three human proofreaders with those of an automatic system, DanProof. Adopting the error categorization scheme of the latter, we look at the accuracy of individual error types and their relative distribution over time, as well as the adequacy of suggested corrections. Finally, we discuss so-called artefact errors introduced by corpus processing, and the potential of DanProof as a corpus cleaning tool for identifying and correcting format conversion, OCR or other compilation errors. In the evaluation, with balanced F1-scores of 77.6 and 67.6 for 1999 texts and 2019 texts, respectively, DanProof achieved a higher recall and accuracy than the individual human annotators, and contributed the largest share of errors not detected by others (16.4% for 1999 and 23.6% for 2019). However, the human annotators had a significantly higher precision. Not counting artifacts, the overall error frequency in the corpus was low ( 0.5%), and less than half in the newer texts compared to the older ones, a change that mostly concerned orthographical errors, with a correspondingly higher relative share of grammatical errors.</abstract>
<identifier type="citekey">bick-etal-2024-man</identifier>
<location>
<url>https://aclanthology.org/2024.sigul-1.24</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>204</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Man or Machine: Evaluating Spelling Error Detection in Danish Newspaper Corpora
%A Bick, Eckhard
%A Blom, Jonas Nygaard
%A Rathje, Marianne
%A Schack, Jørgen
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bick-etal-2024-man
%X This paper evaluates frequency and detection performance for both spelling and grammatical errors in a corpus of published Danish newspaper texts, comparing the results of three human proofreaders with those of an automatic system, DanProof. Adopting the error categorization scheme of the latter, we look at the accuracy of individual error types and their relative distribution over time, as well as the adequacy of suggested corrections. Finally, we discuss so-called artefact errors introduced by corpus processing, and the potential of DanProof as a corpus cleaning tool for identifying and correcting format conversion, OCR or other compilation errors. In the evaluation, with balanced F1-scores of 77.6 and 67.6 for 1999 texts and 2019 texts, respectively, DanProof achieved a higher recall and accuracy than the individual human annotators, and contributed the largest share of errors not detected by others (16.4% for 1999 and 23.6% for 2019). However, the human annotators had a significantly higher precision. Not counting artifacts, the overall error frequency in the corpus was low ( 0.5%), and less than half in the newer texts compared to the older ones, a change that mostly concerned orthographical errors, with a correspondingly higher relative share of grammatical errors.
%U https://aclanthology.org/2024.sigul-1.24
%P 204-211
Markdown (Informal)
[Man or Machine: Evaluating Spelling Error Detection in Danish Newspaper Corpora](https://aclanthology.org/2024.sigul-1.24) (Bick et al., SIGUL-WS 2024)
ACL