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 107515146, Article, New stamp for 1965, page 23 1964-12-15, The Canberra Times (ACT : 1926 - 1995), 58 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
New stamp	New stamp	New stamp
for 1965	for 1965	for 1965
A postage stamp to com	A postage stamp to com-	A postage stamp to commemorate
memorate International Co	memorate International Co-	International Co-operation
operation Year would be	operation Year would be	Year would be
issued by the Post Office	issued by the Post Office	issued by the Post Office
next year, the Postmaster	next year, the Postmaster-	next year, the Postmaster
General. Mr. Hulme. said	General, Mr. Hulme, said	General. Mr. Hulme. said
yesterday.	yesterday.	yesterday.
The United Nations Gen	The United Nations Gen-	The United Nations General
eral Assembly had design	eral Assembly had design-	Assembly had design
ated 1965 as International	ated 1965 as International	ated 1965 as International
Co-operation Year and it	Co-operation Year and it	Co-operation Year and it
was also the 20th annivers	was also the 20th annivers-	was also the 20th anniversary
ary o£ the U.N., he said, j	ary of the U.N., he said.	of the U.N. he said,

Identified overProof corrections	OF
Identified overProof non-corrections

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	47	97.9	100.0	100.0
Searchability of unique words	37	97.3	100.0	100.0
Weighted Words		98.4	100.0	100.0

Article ID 141979525, Article, NEW POSTAGE STAMPS WILL DEPICT BIRDS, page 8 1964-02-07, Western Herald (Bourke, NSW : 1887 - 1970), 127 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
NEW POSTAGE . STAMPS \|	NEW POSTAGE STAMPS	NEW POSTAGE . STAMPS
f WILL DEPICT BIRDS j	WILL DEPICT BIRDS	of WILL DEPICT BIRDS j
i-iWaas^jp be	Australian birds will be	i-iWaas^jp be
depicted? on three multi	depicted on three multi-	depicted? on three multi
coloured stamps to be issued	coloured stamps to be issued	coloured stamps to be issued
on Wednesday, 11th Marxdi,	on Wednesday, 11th March,	on Wednesday, 11th March,
at all Post Offices. AnnonnT.	at all Post Offices. Announ-	at all Post Offices. AnnonnT.
icing this, the Postmaster.	cing this, the Postmaster-	king this, the Postmaster.
Gr^ieral. - Mr. Hiilme. said	General, Mr. Hulme, said	General. Mr Hulme. said
that the Magpie, the gaiafe:	that the Magpie, the galah	that the Magpie, the garage:
and the blue wren would jbe	and the blue wren would be	and the blue wren would be
shown in natural coiout^	shown in natural colours	shown in natural colours
in denominations, respecti	in denominations, respecti-	in denominations, respectively,
vely, of 9d_, 1/6., :and 2/5J	vely, of 9d, 1/6., and 2/5.	of 9d, 1/6., and 25
The* magpie design ^xrouldi	The magpie design would	The magpie design executed
feature the black and white	feature the black and white	feature the black and white
bird framed by eucalypts;	bird framed by eucalypts ;	bird framed by eucalypts;
the eal^ coloured ros^-l^l	the galah, coloured rose-red	the gaily coloured vessels
and grey, c would be ; shown	and grey, would be shown	and grey, c would be shown
perched on a dead tree; and	perched on a dead tree; and	perched on a dead tree; and
the blue' wren would be de	the blue wren would be de-	the blue' wren would be depicted
picted on a bSckground -of j	picted on a background of	on a background of j
bracks	bracken fern. Mr. Hulme	bracks
said that the stamps weie	said that the stamps were	said that the stamps were
deigned by Mrs-B: Tem\|fle	deigned by Mrs. H. Temple-	designed by Mrs-B: Temple
Watts, of Canbeira, a, highly	Watts, of Canberra, a highly	Watts, of Canberra, a, highly
regardedAustralian-bird ar	regarded Australian bird ar-	regardedAustralian-bird artist.
tist. ; ; ' .?.'?'??r	tist.	; ; ' .?.'?'??r

Identified overProof corrections	TEMPLE HULME WERE BACKGROUND GENERAL ARTIST COLOURS RESPECTIVELY CANBERRA MARCH
Identified overProof non-corrections	REGARDED FERN DEIGNED [**VANDALISED] /ROSE/RED\|ROSERED GALAH ANNOUNCING AUSTRALIAN BRACKEN

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	110	77.3	86.4	40.0
Searchability of unique words	68	75.0	88.2	52.9
Weighted Words		76.4	87.5	46.9

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	157	83.5	90.5	42.4
Searchability of unique words	105	82.9	92.4	55.4
Weighted Words		83.0	91.2	48.5

NLA Trial Articles from 1964

Article ID 107515146, Article, New stamp for 1965, page 23 1964-12-15, The Canberra Times (ACT : 1926 - 1995), 58 words, 3 corrections

Article ID 141979525, Article, NEW POSTAGE STAMPS WILL DEPICT BIRDS, page 8 1964-02-07, Western Herald (Bourke, NSW : 1887 - 1970), 127 words, 3 corrections

Accumulated stats for 2 articles from year 1964