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 1196421, Family Notices, Family Notices, page 2 1859-08-24, The South Australian Advertiser (Adelaide, SA : 1858 - 1889), 68 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
BIRTH.	BIRTH.	BIRTH.
On the 19th August, at Vauxhall House, Norwood, tht	On the 19th August, at Vauxhall House, Norwood, the	On the 19th August, at Vauxhall House, Norwood, the
wife of Mr. J. Z. Sellar, of a daughter.	wife of Mr. J. Z. Sellar, of a daughter.	wife of Mr. J. Z. Sellar, of a daughter.
Our Port Agency.-Mr. F. J?. Jones has	OUR PORT AGENCY.—Mr. F. B. Jones has	Our Port Agency Mr. F. J?. Jones has
been appointed inside Reporter and general Agent	been appointed inside Reporter and general Agent	been appointed inside Reporter and general Agent
for the Advertises and Chronicle at Port I	for the ADVERTISER and CHRONICLE at Port	for the Advertiser and Chronicle at Port
Adelaide." Mr. Jones is aho authorised to col-	Adelaide. Mr. Jones is also authorised to col-	Adelaide." Mr. Jones is also authorised to collect
lect accounts for the proprietor^, having been	lect accounts for the proprietors, having been	accounts for the proprietors, having been
furnished with the printed receipts of the Com-	furnished with the printed receipts of the Com-	furnished with the printed receipts of the Company
pany for that purpose.	pany for that purpose.	for that purpose.

Identified overProof corrections	ALSO PROPRIETORS ADVERTISER
Identified overProof non-corrections

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	59	93.2	100.0	100.0
Searchability of unique words	44	93.2	100.0	100.0
Weighted Words		93.5	100.0	100.0

Article ID 1199958, Family Notices, Family Notices, page 2 1859-12-07, The South Australian Advertiser (Adelaide, SA : 1858 - 1889), 109 words, 7 corrections

Identified overProof corrections	COMPANY
Identified overProof non-corrections

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	94	94.7	98.9	80.0
Searchability of unique words	70	98.6	100.0	100.0
Weighted Words		98.8	100.0	100.0

Article ID 3724736, Family Notices, Family Notices, page 2 1859-11-02, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 50 words, 4 corrections

Raw OCR	Human Corrected	overProof Corrected
BIRTHS.	BIRTHS.	BIRTHS.
At Cartsbnry, near Brisbane, on the 31st nit.,	At Cartsbury, near Brisbane, on the 31st ult.,	At Carlsburg, near Brisbane, on the 31st ult.,
]Irs. 0. F. Gerler, of a daughter.	Mrs. C. F. Gerler, of a daughter.	Mrs. C. F. Gerler, of a daughter.
At Brisbane, on the 29th ult., Mrs. W. D.	At Brisbane, on the 29th ult., Mrs. W. D.	At Brisbane, on the 29th ult., Mrs. W. D.
Grimes, of a daughter.	Grimes, of a daughter.	Grimes, of a daughter.
On Sunday, Ootobar 30th, at Rosaville, South	On Sunday, October 30th, at Rosaville, South	On Sunday, October 30th, at Rosaville, South
Brisbane, the wife of Mr. A. J. Hockings of a son.	Brisbane, the wife of Mr. A. J. Hockings of a son.	Brisbane, the wife of Mr. A. J. Hockings of a son.
ff . ?		of . ?

Identified overProof corrections	OCTOBER
Identified overProof non-corrections	CARTSBURY

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	35	88.6	97.1	75.0
Searchability of unique words	21	90.5	95.2	50.0
Weighted Words		90.0	94.0	40.2

Article ID 3725110, Family Notices, Family Notices, page 2 1859-04-20, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 93 words, 7 corrections

Identified overProof corrections	REV SATURDAY CIRCLE JAUNDICE BRISBANE THREE OAKES MAUNSELL BY INST FATHER
Identified overProof non-corrections	MRS

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	81	81.5	98.8	93.3
Searchability of unique words	63	81.0	98.4	91.7
Weighted Words		79.4	98.7	93.6

Article ID 13034277, Article, TOTAL LOSS OF THE SHIP SAPPHIRE., page 6 1859-12-10, The Sydney Morning Herald (NSW : 1842 - 1954), 194 words, 3 corrections

Identified overProof corrections	CLOSE CONTAINING ARE LANDING GREAT DOUGLASS BARE THROUGH
Identified overProof non-corrections	TIN [**VANDALISED]

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	175	89.1	99.4	94.7
Searchability of unique words	109	92.7	99.1	87.5
Weighted Words		92.4	99.1	88.4

Article ID 66334965, Article, BALLARAT DISTRICT ROAD BOARD. Saturday, 2nd April. (Present-Messrs Seal (in the chair) Havery, Baird, Hayden, Laidlaw, M'Phillimy, and Dalgleish.), page 2 1859-04-04, The Star (Ballarat, Vic. : 1855 - 1864), 333 words, 4 corrections

Identified overProof corrections	MCPHILLIMY BLUE NO MINUTES
Identified overProof non-corrections	MPHILLIMY [VANDALISED] BUIRAMBEET [VANDALISED]

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	298	95.6	98.7	69.2
Searchability of unique words	148	97.3	98.6	50.0
Weighted Words		97.7	98.2	25.0

NLA Trial Articles from 1859

Article ID 1196421, Family Notices, Family Notices, page 2 1859-08-24, The South Australian Advertiser (Adelaide, SA : 1858 - 1889), 68 words, 3 corrections

Article ID 1199958, Family Notices, Family Notices, page 2 1859-12-07, The South Australian Advertiser (Adelaide, SA : 1858 - 1889), 109 words, 7 corrections

Article ID 3724736, Family Notices, Family Notices, page 2 1859-11-02, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 50 words, 4 corrections

Article ID 3725110, Family Notices, Family Notices, page 2 1859-04-20, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 93 words, 7 corrections

Article ID 13034277, Article, TOTAL LOSS OF THE SHIP SAPPHIRE., page 6 1859-12-10, The Sydney Morning Herald (NSW : 1842 - 1954), 194 words, 3 corrections

Article ID 66334965, Article, BALLARAT DISTRICT ROAD BOARD. Saturday, 2nd April. (Present-Messrs Seal (in the chair) Havery, Baird, Hayden, Laidlaw, M'Phillimy, and Dalgleish.), page 2 1859-04-04, The Star (Ballarat, Vic. : 1855 - 1864), 333 words, 4 corrections

Accumulated stats for 6 articles from year 1859

Raw OCR	Human Corrected	overProof Corrected
DIED.	DIED.	DIED.
December 4, at Riverton, Sarah Ann, wife of XV. F. Gray,	December 4, at Riverton, Sarah Ann, wife of W. F. Gray,	December 4, at Riverton, Sarah Ann, wife of W. F. Gray,
ol Kapunda, after a long illness.	of Kapunda, after a long illness.	of Kapunda, after a long illness.
December 6, of scarlet fever. Jane, youngest daughter of	December 6, of scarlet fever, Jane, youngest daughter of	December 6, of scarlet fever. Jane, youngest daughter of
C. Byng, Topham-street, Adelaide, aged two years and two	C. Byng, Topham-street, Adelaide, aged two years and two	C. Byng, Topham-street, Adelaide, aged two years and two
months.	months.	months.
Deeember 6, at Glenelg, Holdfast Bay, George Worthington,	December 6, at Glenelg, Holdfast Bay, George Worthington,	December 6, at Glenelg, Holdfast Bay, George Worthington,
Esq., J. P., Senior Solicitor to the Real Property Commis-	Esq., J. P., Senior Solicitor to the Real Property	Esq., J. P., Senior Solicitor to the Real Property Commis-
Commissioners, formerly of Liverpool, aged 70.	Commissioners, formerly of Liverpool, aged 70.	Commissioners, formerly of Liverpool, aged 70.
OUR PORT AGENCY.-Mr. F. B. Jones has	OUR PORT AGENCY.— Mr. F. B. Jones has	OUR PORT AGENCY. Mr. F. B. Jones has
been appointed inside Reporter and general Agent	been appointed inside Reporter and general Agent	been appointed inside Reporter and general Agent
for the ADVERTISER and CHRONICLE at Port	for the ADVERTISER and CHRONICLE at Port	for the ADVERTISER and CHRONICLE at Port
Adelaide, iii?. Jones is also authorised to col-	Adelaide. Mr. Jones is also authorised to	Adelaide, alias. Jones is also authorised to col-
collect accounts for the proprietors, having been	collect accounts for the proprietors, having been	collect accounts for the proprietors, having been
furnished with Hie printed receipt's of the Oom	furnished with the printed receipts of the	furnished with the printed receipts of the Company
nany for that purpose.	Company for that purpose.	for that purpose.

Raw OCR	Human Corrected	overProof Corrected
TOTAL LOSS OF THE 8HIP SAPPHIRE.	TOTAL LOSS OF THE SHIP SAPPHIRE.	TOTAL LOSS OF THE SHIP SAPPHIRE.
]k The Sapphire, ship, 749 tons, Captain Doug.ass, sailed from	The Sapphire, ship, 749 tons, Captain Douglass, sailed from	]k The Sapphire, ship, 749 tons, Captain Douglass, sailed from
/" this port tor Madras, in August last, touching at Port Curtis to	this port for Madras, in August last, touching at Port Curtis to	/" this port for Madras, in August last, touching at Port Curtis to
take in horses. Wo now learn, thronen Captain Jamison, that	take in horses. We now learn, through Captain Jamison, that	take in horses. We now learn, through Captain Jamison, that
she was wrecked on 23rd September. Tho following aro the par-	she was wrecked on 23rd September. The following are the par-	she was wrecked on 23rd September. The following are the particulars
ticulars as reported by that gentleman.	ticulars as reported by that gentleman.	as reported by that gentleman.
" 4 p.m. 6th October, on landug at Hardy's Island, foot marks	"4 p.m. 6th October, on landing at Hardy's Island, foot marks	" 4 p.m. 6th October, on landing at Hardy's Island, foot marks
(boots and biro feet) wero oloso to tho water's edge, evident	(boots and bare feet) were close to the water's edge, evident	(boots and bare feet) were close to the water's edge, evident
marks that persons had left there about three hours before we	marks that persons had left there about three hours before we	marks that persons had left there about three hours before we
landed, also an old tin belonging to a life-boat, tho following	landed, also an old tin belonging to a life-boat, the following	landed, also an old man belonging to a life-boat, the following
was scratched on it. ' The Sapphire was wreokod on	was scratched on it. 'The Sapphire was wrecked on	was scratched on it. The Sapphire was wrecked on
the 23rd September, and the crew left in two boats	the 23rd September, and the crew left in two boats	the 23rd September, and the crew left in two boats
for Port Curtis, dated 6th October.' The next day a bottle	for Port Curtis, dated 6th October.' The next day a bottle	for Port Curtis, dated 6th October.' The next day a bottle
was found hanging to a tree, uontaining four letters and three	was found hanging to a tree, containing four letters and three	was found hanging to a tree, containing four letters and three
locks of hair ; thrco signed by Captain Western, a passenger, and	locks of hair ; three signed by Captain Western, a passenger, and	locks of hair ; three signed by Captain Western, a passenger, and
the other by Thomas Clarke. There was also a small pamphlet	the other by Thomas Clarke. There was also a small pamphlet	the other by Thomas Clarke. There was also a small pamphlet
published in Madras, attached to the bottle. The following aro	published in Madras, attached to the bottle. The following are	published in Madras, attached to the bottle. The following are
copies of the several letters, by which it would appear that the	copies of the several letters, by which it would appear that the	copies of the several letters, by which it would appear that the
unfortunate people were m groat distress.	unfortunate people were in great distress.	unfortunate people were in great distress.

Raw OCR	Human Corrected	overProof Corrected
BALLARAT DISTRICT ROAD BOARD. ¡	BALLARAT DISTRICT ROAD BOARD.	BALLARAT DISTRICT ROAD BOARD. S
Saturday, 2nd April.	Saturday, 2nd April.	Saturday, 2nd April.
(Present-Messrs Seal (in the chair) Havery,	(Present—Messrs Seal (in the chair) Havery,	(Present-Messrs Seal (in the chair) Havery,
Baird, Hayden, Laidlaw, M'PhiÚimy, and	Baird, Hayden, Laidlaw, McPhillimy, and	Baird, Hayden, Laidlaw, McPhillimy, and
Dalgleish.)	Dalgleish.)	Dalgleish.)
Therninutes of the last meeting were read	The minutes of the last meeting were read	The minutes of the last meeting were read
and confirmed. The secretary then read the	and confirmed. The secretary then read the	and confirmed. The secretary then read the
following letters :	following letters :	following letters :
1. From the Roads and Bridges office,	1. From the Roads and Bridges office,	1. From the Roads and Bridges office,
stating that the Amherst road would shortly	stating that the Amherst road would shortly	stating that the Amherst road would shortly
be commenced, and with it a portion of the	be commenced, and with it a portion of the	be commenced, and with it a portion of the
Miners' Rest road.	Miners' Rest road.	Miners' Rest road.
2. From the Registrar-General, acknow	2. From the Registrar-General, acknow-	2. From the Registrar-General, acknowledging
ledging the receipt of the " Bine Book	ledging the receipt of the "Blue Book	the receipt of the " Blue Book
returns."	returns."	returns."
3. From William Watson Boyes, who was	3. From William Watson Boyes, who was	3. From William Watson Boyes, who was
last year collector to the Board, and now	last year collector to the Board, and now	last year collector to the Board, and now
dated his letter from " Pastoria, Kyneton."	dated his letter from "Pastoria, Kyneton."	dated his letter from " Pastoria, Kyneton."
The letter forwarded Mr Boyes' account	The letter forwarded Mr Boyes' account	The letter forwarded Mr Boyes' account
against the Board, and requested immediate	against the Board, and requested immediate	against the Board, and requested immediate
payment.	payment.	payment.
The Board declined to receive Mr Boyes'	The Board declined to receive Mr Boyes'	The Board declined to receive Mr Boyes'
letter.	letter.	letter.
The secretary then presented the collec	The secretary then presented the collec-	The secretary then presented the collectors'
tors' returns which contained the following	tors' returns which contained the following	returns which contained the following
statistics :	statistics :	statistics : No
Ko of ratepayers, 720.	No of ratepayers, 720.	of ratepayers, 720.
Alienated land (uncultivated) 51,550 acres.	Alienated land (uncultivated) 51,550 acres.	Alienated land (uncultivated) 51,550 acres.
Alienated land (cultivated) 26,779 acres.	Alienated land (cultivated) 26,779 acres.	alienated land (cultivated) 26,779 acres.
Amount of assessment, £1623 3s 2d.	Amount of assessment, £1823 3s 2d.	Amount of assessment, £1623 3s 2d.
Amount collected, £1816 15s 2d.	Amount collected, £1816 15s 2d.	Amount collected, £1816 15s 2d.
On the motion of Mesfrs Ilavery and	On the motion of Messrs, Havery and	On the motion of Messrs Havery and
Baird, the returns were received, and the re	Baird, the returns were received, and the re-	Baird, the returns were received, and the return
turn of the bond ordered.	turn of the bond ordered.	of the bond ordered.
The next business was to open tenders ;	The next business was to open tenders ;	The next business was to open tenders ;
the result of which was as follows :	the result of which was as follows :	the result of which was as follows:
Contract 21, on the Lexton road, Burn &	Contract 21, on the Lexton road, Burn &	Contract 21, on the Lexton road, Burn &
Co, £207.	Co, £207.	Co, £207.
Contract 22, near Fry's Mill, between	Contract 22, near Fry's Mill, between	Contract 22, near Fry's Mill, between
Ascot and Buirambeet; McNamara, £169.	Ascot and Buirambeet ; McNamara, £169.	Ascot and Burrambeet; McNamara, £169.
Mr Havery then proposed, and Mr	Mr. Havery then proposed, and Mr.	Mr Havery then proposed, and Mr
M'Phillimy seconded a motion calling far	M'Phillimy seconded a motion calling for	McPhillimy seconded a motion calling for
tenders for a piece of road near Lannigan's,	tenders for a piece of road near Lannigan's,	tenders for a piece of road near Lannigan's,
at Glendaruel.-Carried.	at Glendaruel.-- Carried.	at Glendaruel. Carried.
The next subject brought forward was the	The next subject brought forward was the	The next subject brought forward was the
having an office for the Board ou Ballarat. It	having an office for the Board on Ballarat. It	having an office for the Board on Ballarat. It
was, however, postponed till the next meet	was, however, postponed till the next meet-	was, however, postponed till the next meeting.
ing.	ing.
Mr M*PhiUimy moved and Mr Havery	Mr. M'Phillimy moved and Mr. Havery	Mr McPhillamy moved and Mr Havery
seconded " That £300 be set aside as a fund	seconded "That £300 be set aside as a fund	seconded " That £300 be set aside as a fund
for the maintenance of roads." Carried.	for the maintenance of roads." Carried.	for the maintenance of roads." Carried.
Mr Laidlaw moved and Mr Baird seconded,	Mr. Laidlaw moved and Mr. Baird seconded,	Mr Laidlaw moved and Mr Baird seconded,
" That tenders be called for a portion of	"That tenders be called for a portion of	" That tenders be called for a portion of
road near Webb's property." Carried.	road near Webb's property." Carried.	road near Webb's property." Carried.
Mr M'Phillimy moved and Mr Laidlaw	Mr. M'Phillimy moved and Mr. Laidlaw	Mr McPhillimy moved and Mr Laidlaw
seconded, *. Th it the engineer's report on the	seconded, "That the engineer's report on the	seconded, 2. That the engineer's report on the
road near the agricultural society reserve,	road near the agricultural society reserve,	road near the agricultural society reserve,
be adopted." Carried.	be adopted." Carried.	be adopted." Carried.
The Board.shortly after adjourned.	The Board shortly after adjourned.	The Board. shortly after adjourned.

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	742	91.9	98.9	86.8
Searchability of unique words	455	93.4	98.9	83.0
Weighted Words		93.9	98.6	77.7

Raw OCR	Human Corrected	overProof Corrected
BIRTH.	BIRTH.	BIRTH.
At her residence, Maneroo, on the 27th March,	At her residence, Maneroo, on the 27th March,	At her residence, Maneroo, on the 27th March,
Jin. P. Mauniell, late (if Brisbano, of a son.	Mrs. P. Maunsell, late of Brisbane, of a son.	Jin. P. Maunsell, late (of Brisbane, of a son.
MARRIED,	MARRIED,	MARRIED,
On the 12th ¡nut, hy the i'athor of tho bride,	On the 12th inst, by the father of the bride,	On the 12th Inst, by the father of the bride,
George Oakoa Beardmore, Esq., of Cooroora,	George Oakes Beardmore, Esq., of Cooroora,	George Oakes Beardmore, Esq., of Cooroora,
Darling Downs, to Lydia, second daughter of	Darling Downs, to Lydia, second daughter of	Darling Downs, to Lydia, second daughter of
the Rav. J. T. Waraker, of Ipswich.	the Rev. J. T. Waraker, of Ipswich.	the Rev. J. T. Waraker, of Ipswich.
DIED.	DIED.	DIED.
Oa S¿turdav, the 2nd April, 1859, at his resi-	On Saturday, the 2nd April, 1859, at his resi-	On Saturday, the 2nd April, 1859, at his residence,
dence, Gayndah, Burnett District, Mr, Michael	dence, Gayndah, Burnett District, Mr Michael	Gayndah, Burnett District, Mr Michael
Power, aged 37 years, after an illness of thrae	Power, aged 37 years, after an illness of three	Power, aged 37 years, after an illness of three
weeks, of j.undice, leaving a devoted wife, four	weeks, of jaundice, leaving a devoted wife, four	weeks, of jaundice, leaving a devoted wife, four
children, and a large cirole of friends to lament	children, and a large circle of friends to lament	children, and a large circle of friends to lament
their loss.	their loss.	their loss.