@inproceedings{reynaert-2016-ocr,
title = "{OCR} Post-Correction Evaluation of Early {D}utch Books Online - Revisited",
author = "Reynaert, Martin",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1154",
pages = "967--974",
abstract = "We present further work on evaluation of the fully automatic post-correction of Early Dutch Books Online, a collection of 10,333 18th century books. In prior work we evaluated the new implementation of Text-Induced Corpus Clean-up (TICCL) on the basis of a single book Gold Standard derived from this collection. In the current paper we revisit the same collection on the basis of a sizeable 1020 item random sample of OCR post-corrected strings from the full collection. Both evaluations have their own stories to tell and lessons to teach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reynaert-2016-ocr">
<titleInfo>
<title>OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited</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>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present further work on evaluation of the fully automatic post-correction of Early Dutch Books Online, a collection of 10,333 18th century books. In prior work we evaluated the new implementation of Text-Induced Corpus Clean-up (TICCL) on the basis of a single book Gold Standard derived from this collection. In the current paper we revisit the same collection on the basis of a sizeable 1020 item random sample of OCR post-corrected strings from the full collection. Both evaluations have their own stories to tell and lessons to teach.</abstract>
<identifier type="citekey">reynaert-2016-ocr</identifier>
<location>
<url>https://aclanthology.org/L16-1154</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>967</start>
<end>974</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited
%A Reynaert, Martin
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F reynaert-2016-ocr
%X We present further work on evaluation of the fully automatic post-correction of Early Dutch Books Online, a collection of 10,333 18th century books. In prior work we evaluated the new implementation of Text-Induced Corpus Clean-up (TICCL) on the basis of a single book Gold Standard derived from this collection. In the current paper we revisit the same collection on the basis of a sizeable 1020 item random sample of OCR post-corrected strings from the full collection. Both evaluations have their own stories to tell and lessons to teach.
%U https://aclanthology.org/L16-1154
%P 967-974
Markdown (Informal)
[OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited](https://aclanthology.org/L16-1154) (Reynaert, LREC 2016)
ACL