Notes

Accuracy of OCR and overProof is measured in comparison with the human corrections. We know human corrections in this sample are incomplete, and themselves contain errors, but they are the best we could find automatically from the NLA newspapers corpus, tagged as completely corrected then further filtered to those with at least 3 corrections, at least 40% of lines corrected and lowest third percentage of non-dictionary words.
Accuracy is measured by a separate process from that used to colour words in this output: the colouring process is heuristic, and not completely accurate.
Colour legend:
Text - OCR text corrected by human and/or overProof
Text - human and/or overProof corrections
Text - discrepencies between human and/or overProof
Text - human corrections not applied by overProof
Identified overProof corrections are calculated by the statistical calculation process, and shows those words changed by overProof which ALSO match human corrections. As human corrections are often wrong and incomplete, so too is this list.
Identified overProof non-corrections are calculated by the statistical calculation process, and shows those words in the overProof output which DO NOT MATCH human corrections. As human corrections are often wrong and incomplete, so too is this list. Words marked as [**VANDALISED] are those which have been changed by overProof but not by the human correction; as before, a missed human correction will be (incorrectly) classified as vandalisation by overProof.
Searchability of unique words refers to the distinct words in an article, and how many are present before and after correction. It is measure of how many of the words within an article could be used to find the article using a search engine.
Weighted Words refers to a calculation in which common words count for little (a fraction of a word) and unusual words count for more, in proportion to the log of the inverse of their frequency in the corpus. It may be an indicator of how well distinctive words in an article can be searched before and after correction.

Article ID 2183507, Article, GOVERNMENT ADVERTISEMENT., page 1 1824-12-16, The Sydney Gazette and New South Wales Advertiser (NSW : 1803 - 1842), 98 words, 4 corrections

Raw OCR	Human Corrected	overProof Corrected
C,OVEF N MENT A DVERT1RE jl ENT.	GOVERNMENT ADVERTISEMENT.	COVER N MENT A ADVERTISE M ENT.
Colonial Secke-xak.y's.Ofhoç, L>Ecç3iBj;n 15, 1821.	Colonial Secretary's Office, December 15, 1824.	Colonial Secke-xak.y's.Ofhoç, L>Ecç3iBj;n 15, 1821.
"(HUE i> ln-rel>> .given, thai the IJGliT	NOTICE is hereby given, that the LIGHT-	"(HUE is entirely given, that the IJGliT
,__ _ M ('USE, between the (à real Mouillée ck	HOUSE between the Great Mouillee or	in H M ('USE, between the (à real Mouille ck
Rcnih'n Battery, and Three Anchor Ba\, under the	Moulin Battery, and Three Anchor Bay, under the	Rcnih'n Battery, and Three Anchor Bay, under the
Li'li's Rump, at the Entrance of Table Bay, Cape	Lion's Rump, at the Entrance of Table Bay, Cape	Lion's Rump, at the Entrance of Table Bay, Cape
of (»lind !ln\|,p, having boen completed on the 9th,	of Good Hope, having been completed on the 9th,	of (land !ln\|,p, having been completed on the 9th,
t1 e Lighting thereof commenced on Mi.miuy, the	the Lighting thereof commenced on Monday, the	t e Lighting thereof commenced on Monday, the
12ili oi'lasl April.	12th of last April.	12th of last April.
. The following Directions under which Vectis	The following Directions under which Vessels	The following Directions under which Vectis
moy cuter Table Barlil the Nifi'nt, ar.e ihertioie	may enter Table Bay, in the Night, are therefore	may enter Table Barker the Nifi'nt, are therefore
iDKile public f"r gênerai Information.	made public for general Information.	iDKile public for general Information.
h) Command of His En-ellenc-v I tie Governor,	By Command of His Excellency the Governor,	by Command of His Excellency I the Governor,
F. C-run.r,u KNjColouud Secretar}.	F. GOULBURN, Colonial Secretary.	F. Canungra KNjColouud Secretary.

Identified overProof corrections	THAT SECRETARY IN FOR IS THEREFORE BEEN ARE LAST EXCELLENCY MAY ENTER GENERAL BY LIONS THE12TH MONDAY
Identified overProof non-corrections	DECEMBER HEREBY VESSELS NIGHT GOULBURN GOOD HOPE MOUILLEE LIGHTHOUSE MADE NOTICE SECRETARYS GREAT OR OFFICE MOULIN GOVERNMENT ADVERTISEMENT

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	83	51.8	75.9	50.0
Searchability of unique words	66	47.0	72.7	48.6
Weighted Words		52.0	75.3	48.6

NLA Trial Articles from 1824

Article ID 2183507, Article, GOVERNMENT ADVERTISEMENT., page 1 1824-12-16, The Sydney Gazette and New South Wales Advertiser (NSW : 1803 - 1842), 98 words, 4 corrections

Accumulated stats for 1 articles from year 1824