OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited

Martin Reynaert

OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited

Martin Reynaert

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

4 Citations (Scopus)

228 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)
Editors	Calzolari
Publisher	ELRA
Pages	967-974
Number of pages	8
Publication status	Published - 2016
Event	International Conference on Language Resources and Evaluation 2016: 10th edition - Grand Hotel Bernardin Conference Center, Portoroz, Slovenia Duration: 23 May 2016 → 28 May 2016 Conference number: 10 http://lrec2016.lrec-conf.org/en/

Conference

Conference	International Conference on Language Resources and Evaluation 2016
Abbreviated title	LREC 2016
Country/Territory	Slovenia
City	Portoroz
Period	23/05/16 → 28/05/16
Internet address	http://lrec2016.lrec-conf.org/en/

Keywords

TICCL
OCR post-correction
evaluation
EDBO
Nederlab
CLARIAH

Access to Document

LREC2016.EDBOeval.FinalSubmittedVersion.redownloaded20160318Licence: Unspecified

Cite this

@inproceedings{29cbd25aa16348cbb1c78745cf08ddec,

title = "OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited",

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.",

keywords = "TICCL, OCR post-correction, evaluation, EDBO, Nederlab, CLARIAH",

author = "Martin Reynaert",

year = "2016",

language = "English",

pages = "967--974",

editor = "Calzolari",

booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)",

publisher = "ELRA",

note = "International Conference on Language Resources and Evaluation 2016 : 10th edition, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",

url = "http://lrec2016.lrec-conf.org/en/",

}

TY - GEN

T1 - OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited

AU - Reynaert, Martin

N1 - Conference code: 10

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

KW - TICCL

KW - OCR post-correction

KW - evaluation

KW - EDBO

KW - Nederlab

KW - CLARIAH

UR - http://www.lrec-conf.org/proceedings/lrec2016/summaries/596.html

M3 - Conference contribution

SP - 967

EP - 974

BT - Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)

A2 - Calzolari, null

PB - ELRA

T2 - International Conference on Language Resources and Evaluation 2016

Y2 - 23 May 2016 through 28 May 2016

ER -

OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Synergy of Nederlab and @PhilosTEI: diachronic and multilingual Text-Induced Corpus Clean-up

Cite this