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 142371030, Article, POSTAGE STAMP FOR 50th ANNIVERSAY OF CANBERRA, page 8 1962-11-16, Western Herald (Bourke, NSW : 1887 - 1970), 122 words, 6 corrections

Raw OCR	Human Corrected	overProof Corrected
POSTAGE STAMP FOR	POSTAGE STAMP FOR	POSTAGE STAMP FOR
50th ANNIVERSAY	50th ANNIVERSAY	50th ANNIVERSARY
OF CANBERRA	OF CANBERRA	OF CANBERRA
- A 5d. postage stamp will	A 5d. postage stamp will	A 5d. postage stamp will
be issued ea^y riexfcyejgtr !to	be issued early next year to	be issued easy riexfcyejgtr to
commemorate fch% 50th- Q&ki-	commemorate the 50th an-	commemorate the 50th- Oki-
niversary of Canberra/' -in.	niversary of Canberra. In	niversary of Canberra -in.
stating this, the Postmaster-:	stating this, the Postmaster-	stating this, the Postmaster-:
General, Mr; Davidson, said	General, Mr. Davidson, said	General, Mr; Davidson, said
that the. official ceremony,	that the official ceremony	that the. official ceremony,
held on 12th March; 1913,	held on 12th March, 1913,	held on 12th March; 1913,
marked; ttie beginning of	marked the beginning of	marked; the beginning of
operations' for the estab	operations for the estab-	operations for the establishment
lishment of the seat of gov	lishment of the seat of gov-	of the seat of government
ernment at Canberra,; The	ernment at Canberra. The	at Canberra, The
design of* the new stamp	design of the new stamp	design of the new stamp
will comprise the Coatof	will comprise the Coat-of-	will comprise the Coat of
Arms of r the city and a por-:	Arms of the city and a por-	Arms of r the city and a portrait
trait of the late Walter:	trait of the late Walter	of the late Walter:
Burley Griffin, ' American	Burley Griffin, American	Burley Griffin, American
architect,- upon whose plan	architect, upon whose plan	architect,- upon whose plan
Of layout the development	of layout the development	of layout the development
of the city of Canberra has	of the city of Canberra has	of the city of Canberra has
been based. Further paiv	been based. Further par-	been based. Further particulars
ticulars of the stamp, and	ticulars of the stamp, and	of the stamp, and
the date of Issue, will be	the date of issue, will be	the date of issue will be
announced when production	announced when production	announced when production
is further advanced.	is further advanced.	is further advanced.

Identified overProof corrections	COAT PORTRAIT PARTICULARS ANNIVERSARY
Identified overProof non-corrections	YEAR EARLY NEXT ANNIVERSAY [**VANDALISED]

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	108	90.7	96.3	60.0
Searchability of unique words	67	89.6	94.0	42.9
Weighted Words		91.3	95.0	42.9

NLA Trial Articles from 1962

Article ID 142371030, Article, POSTAGE STAMP FOR 50th ANNIVERSAY OF CANBERRA, page 8 1962-11-16, Western Herald (Bourke, NSW : 1887 - 1970), 122 words, 6 corrections

Accumulated stats for 1 articles from year 1962