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 116424296, Article, Goanna oil is going places, page 2 1983-08-20, The Canberra Times (ACT : 1926 - 1995), 459 words, 4 corrections

Identified overProof corrections	TWO WINTERGREEN INDICATIONS LAST SPORTSPEOPLE
Identified overProof non-corrections

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	417	98.3	100.0	100.0
Searchability of unique words	227	97.8	100.0	100.0
Weighted Words		98.3	100.0	100.0

NLA Trial Articles from 1983

Article ID 116424296, Article, Goanna oil is going places, page 2 1983-08-20, The Canberra Times (ACT : 1926 - 1995), 459 words, 4 corrections

Accumulated stats for 1 articles from year 1983

Raw OCR	Human Corrected	overProof Corrected
Joseph Cornelius Marconi, founder	Joseph Cornelius Marconi, founder	Joseph Cornelius Marconi, founder
of Goanna bush remedies.	of Goanna bush remedies.	of Goanna bush remedies.
Goanna oil is	Goanna oil is	Goanna oil is
going places	going places	going places
X WO of Australia's most popular and sworn	TWO of Australia's most popular and sworn-	X TWO of Australia's most popular and sworn
by bush medicines, Goanna-oil liniment and	by bush medicines, Goanna-oil liniment and	by bush medicines, Goanna-oil liniment and
Goanna salve, are generating a large amount of	Goanna salve, are generating a large amount of	Goanna Salve, are generating a large amount of
interest in England and the United States, the	interest in England and the United States, the	interest in England and the United States, the
new owner of J. C. Marconi, the manufacturer	new owner of J. C. Marconi, the manufacturer	new owner of J. C. Marconi, the manufacturer
I of the products, said in Canberra this week.	of the products, said in Canberra this week.	of the products, said in Canberra this week.
"It is amazing how many requests we get by	"It is amazing how many requests we get by	"It is amazing how many requests we get by
mail for the liniment and salve — some from	mail for the liniment and salve — some from	mail for the liniment and salve — some from
! people who used it while they were stationed in	people who used it while they were stationed in	people who used it while they were stationed in
\| Australia during the war, Australians who have	Australia during the war, Australians who have	Australia during the war, Australians who have
moved overseas and more recently, sportspcoplc	moved overseas and more recently, sportspeople	moved overseas and more recently, sportspeople
and physiotherapists who have been introduced 1	and physiotherapists who have been introduced	and physiotherapists who have been introduced 1
to it by Australian sportsmen and sportswomen," B	to it by Australian sportsmen and sportswomen,"	to it by Australian sportsmen and sportswomen," B
said Mr Euan Murdoch. g	said Mr. Euan Murdoch.	said Mr Euan Murdoch. g
"We now use a pharmaceutical company to I	"We now use a pharmaceutical company to	We now use a pharmaceutical company to 1
package the product and though it is true that	package the product and though it is true that	package the product and though it is true that
it is no longer manufactured on a cottage	it is no longer manufactured on a cottage	it is no longer manufactured on a cottage
industry basis, the traditional formulations arc	industry basis, the traditional formulations are	industry basis, the traditional formulations are
still faithfully followed," Mr Murdoch said.	still faithfully followed," Mr Murdoch said.	still faithfully followed," Mr Murdoch said.
"The only change is that when the goanna	"The only change is that when the goanna	"The only change is that when the goanna
became a protected species, oil of wintergrecn	became a protected species, oil of wintergreen	became a protected species, oil of wintergreen
was substituted."	was substituted."	was substituted."
Developed by a Brisbane inventor and manu	Developed by a Brisbane inventor and manu-	Developed by a Brisbane inventor and manufacturing
facturing chemist, Mr Joseph Marconi, the prod	facturing chemist, Mr Joseph Marconi, the prod-	chemist, Mr Joseph Marconi, the products
ucts have been based on proven natural ingre	ucts have been based on proven natural ingre-	have been based on proven natural ingredients.
dients. During his extensive travels throughout	dients. During his extensive travels throughout	During his extensive travels throughout
Australia Mr Marconi saw the need for an	Australia Mr Marconi saw the need for an	Australia Mr Marconi saw the need for an
effective bush cure-all and in 1910, Goanna Oil,	effective bush cure-all and in 1910, Goanna Oil,	effective bush cure-all and in 1910, Goanna Oil,
"a chemist shop in a bottle", was introduced.	"a chemist shop in a bottle", was introduced.	a chemist shop in a bottle was introduced.
The liniment is recommended for temporary	The liniment is recommended for temporary	The liniment is recommended for temporary
relief of backache, rheumatism, arthritis and	relief of backache, rheumatism, arthritis and	relief of backache, rheumatism, arthritis and
lumbago. The salve is recommended for the	lumbago. The salve is recommended for the	lumbago. The salve is recommended for the
temporary relief of eczema, athlete's foot,	temporary relief of eczema, athlete's foot,	temporary relief of eczema, athletes foot,
rashes, bruises, nasal congestion and abrasions.	rashes, bruises, nasal congestion and abrasions.	rashes, bruises, nasal congestion and abrasions.
A new product, developed three years ago and	A new product, developed three years ago and	A new product, developed three years ago and
proving very popular, is Goanna Sports Rub.	proving very popular, is Goanna Sports Rub.	proving very popular, is Goanna Sports Rub.
"Ldst year more than 200,000 bottles of the	"Last year more than 200,000 bottles of the	"Last year more than 200,000 bottles of the
salve and liniment were sold arid present indica	salve and liniment were sold and present indica-	salve and liniment were sold and present indications
j tions are that we will double that total this year,"	tions are that we will double that total this year,"	are that we will double that total this year,"
Mr Murdoch said.	Mr. Murdoch said.	Mr Murdoch said.
"It is available through chemists and health	"It is available through chemists and health	"It is available through chemists and health
food shops in Australia and if negotiations,	food shops in Australia and if negotiations,	food shops in Australia and if negotiations,
presently under way in the United States, Eng	presently under way in the United States, Eng-	presently under way in the United States, England
land and the Philippines are successful, it will	land and the Philippines are successful, it will	and the Philippines are successful, it will
be made under licence overseas.	be made under licence overseas.	be made under licence overseas.
"Word of mouth has always been our biggest	"Word of mouth has always been our biggest	"Word of mouth has always been our biggest
seller and we have received some incredible	seller and we have received some incredible	seller and we have received some incredible
letters from clients in Australia and overseas.	letters from clients in Australia and overseas.	letters from clients in Australia and overseas.
"There are not many companies, I would	"There are not many companies, I would	"There are not many companies, I would
wager, that would receive a S20 note pinned to	wager, that would receive a $20 note pinned to	wager that would receive a 820 note pinned to
an order asking for their product, from Canada.	an order asking for their product, from Canada.	an order asking for their product, from Canada.
"In 1985 it will be the 75th anniversary of the	"In 1985 it will be the 75th anniversary of the	"In 1935 it will be the 75th anniversary of the
company and at the moment I am collecting all	company and at the moment I am collecting all	company and at the moment I am collecting all
sorts of memorabilia — old bottles, tins, advertis	sorts of memorabilia — old bottles, tins, advertis-	sorts of memorabilia — old bottles, tins, advertis-
ing leaflets ... and hope to produce a Goanna	ing leaflets . . . and hope to produce a Goanna	ing leaflets ... and hope to produce a Goanna
booklet. If anyone has anything that could be of	booklet. If anyone has anything that could be of	booklet. If anyone has anything that could be of
interest then I would be glad to receive it. B	interest then I would be glad to receive it.	interest then I would be glad to receive it. B
"If they can telephone Brisbane 441481 I will B	"If they can telephone Brisbane 441481 I will	"If they can telephone Brisbane 441481 I will B
certainly be glad to talk with them." \|	certainly be glad to talk with them."	certainly be glad to talk with them." a
GARY SCHOLES	— GARY SCHOLES	GARY SCHOLES