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 672786, Family Notices, Family Notices, page 3 1853-09-14, The Maitland Mercury and Hunter River General Advertiser (NSW : 1843 - 1893), 115 words, 4 corrections

Identified overProof corrections	FRANCES MCDONALD MONTHS TWELVE ESQ HIM
Identified overProof non-corrections	CLODE

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	103	87.4	98.1	84.6
Searchability of unique words	68	89.7	98.5	85.7
Weighted Words		90.3	98.4	83.5

Article ID 3714424, Family Notices, Family Notices, page 3 1853-06-04, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 84 words, 4 corrections

Raw OCR	Human Corrected	overProof Corrected
BIRTHS,	BIRTHS.	BIRTHS,
At Kangaroo Point, Brisbine, on the 23th	At Kangaroo Point, Brisbane, on the 28th	At Kangaroo Point, Brisbane, on the 28th
Miy. Mrs. Richard B. Sheridan, of a son. '	May, Mrs. Richard B. Sheridan, of a son.	May. Mrs. Richard B. Sheridan, of a son.
At the residí nee «if Mr. John Harris. South	At the residence of Mr. John Harris, South	At the residence of Mr. John Harris. South
Brisbane, on the 29th Miy, Mrs. \V. Underwood,	Brisbane, on the 28th May, Mrs. W. Underwood,	Brisbane, on the 29th May, Mrs. W. Underwood,
of a daughter. »	of a daughter.	of a daughter.
At South Brisbane, on the 30th ult., Mrs.	At South Brisbane, on the 30th ult., Mrs.	At South Brisbane, on the 30th ult., Mrs.
Mercer, of a daughter.	Mercer, of a daughter.	Mercer, of a daughter.
, MARRIED.	MARRIED.	MARRIED.
At Telemon, on the 1st of June, by the ltev.	At Telemon, on the 1st of June, by the Rev.	At Telemon, on the 1st of June, by the Rev.
II. O.'lrwin, Alfred William Compigne, lisq., of	H. O. Irwin, Alfred William Compigne, Esq., of	R. Sherwin, Alfred William Compigne, Esq., of
Niudoomb.igh, to Jessie Lambert, second daugh-	Nindooinbagh, to Jessie Lambert, second daugh-	Niudoomb.igh, to Jessie Lambert, second daughter
ter of Thomas Cullins, Esq., of Telemon, I/>gan	ter of Thomas Collins, Esq., of Telemon, Logan	of Thomas Collins, Esq., of Telemon, Logan
River.	River.	River.

Identified overProof corrections	COLLINS REV LOGAN MAY RESIDENCE
Identified overProof non-corrections	IRWIN NINDOOINBAGH

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	69	84.1	97.1	81.8
Searchability of unique words	41	82.9	95.1	71.4
Weighted Words		83.1	94.4	66.7

Article ID 4788777, Family Notices, Family Notices, page 4 1853-01-07, The Argus (Melbourne, Vic. : 1848 - 1957), 82 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
ilIUTHS.	BIRTHS.	BIRTHS.
On Wednesday, the 6tl» lnstunt, «ra » Henry, of a	On Wednesday, the 5th instant, Mrs D Seary, of a	On Wednesday, the 6th instant, Mrs J Henry, of a
son.	son.	son.
DIED.	DIED.	DIED.
On the Gtb Inst, at the residence or his «ni, on th*	On the 6th inst, at the residence of his son, on the	On the 6th Inst, at the residence of his and, on the
Werri Creole, Mr Huy Colo, lite or llarrow-oii.	Merri Creek, Mr Guy Cole, late of Harrow-on-	Werris Creole, Mr Guy Cole, late of Harrow-road.
the-Hill, Middlesex, Unglnud, lu the colily tuli.l	the-Hill, Middlesex, England, in the eighty-third	the-Hill, Middlesex, England, in the colony this
year of lils URO.	year of his age.	year of his age.
On «io fttb instant th> intuit ron of II. «liney	On the 5th instant the infant son of H. Slaney	On the 6th instant the infant son of H. Slaney
Esq , ol Quceu-btiett, alelí .luruu.	Esq., of Queen-street, Melbourne.	Esq , of Queen-street, lately during.
r* On the Gili Inatinf, i.t St. Killin. William. Hi«	On the 6th instant, at St. Kilda, William, the	a On the 6th Instant, at St. Kilda. William. the
infant son of Mr Ocorgo Diuinutt, drspor, Cullin*	infant son of Mr George Dunnett, draper, Collins	infant son of Mr George Dunnett, draper, Collins
street, iified l8 moulin.	street, aged 18 months.	street, lifted 18 months.

Identified overProof corrections	COLLINS DRAPER LATE MONTHS SLANEY ENGLAND IN GUY HARROW GEORGE MRS BIRTHS AGE KILDA /QUEEN/STREET\|QUEENSTREET DUNNETT COLE
Identified overProof non-corrections	SEARY CREEK MERRI /EIGHTY/THIRD\|EIGHTYTHIRD MELBOURNE AGED

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	71	47.9	88.7	78.4
Searchability of unique words	43	46.5	86.0	73.9
Weighted Words		46.5	85.4	72.7

Article ID 4796712, Article, THE IRON ROADS OF AUSTRALIA. To the Editor of the Argus., page 5 1853-09-07, The Argus (Melbourne, Vic. : 1848 - 1957), 273 words, 9 corrections

Raw OCR	Human Corrected	overProof Corrected
THE IRON ROADS OF AUSTRALIA.	THE IRON ROADS OF AUSTRALIA.	THE IRON ROADS OF AUSTRALIA.
To the Editor o/ the Argus.	To the Editor of the Argus.	To the Editor of the Argus.
Sir,-Ai tho railway from Geelong must shortly be	Sir,—As the railway from Geelong must shortly be	Sir-As the railway from Geelong must shortly be
commenced, tnd th« Important subject of the breadth	commenced, and the important subject of the breadth	commenced, and the important subject of the breadth
of gu»go li now occupying the attention or the Council,	of guage is now occupying the attention of the Council,	of gauge is now occupying the attention of the Council,
It may perhtp» be In the powor or lorne of your corre	it may perhaps be in the power of some of your corre-	It may perhaps be in the power or some of your corre
i\|K>ndcnt! to furnlih details of the working of t' e loverai	spondents to furnish details of the working of the several	i\|K>ndcnt! to furnish details of the working of the several
systents u shown by actual experience. Thii question	systems as shown by actual experience. This question	systems u shown by actual experience. This question
is, at tho prcrent time, of very great moment. The day	is, at the present time, of very great moment. The day	is, at the present time, of very great moment. The day
ii not far dlltont whin ono vait chain of raliway com-	is not far distant when one vast chain of railway com-	is not far distant when no vast chain of railway communication
munication muit connect tho townt of Melbourne,	munication must connect the towns of Melbourne,	must connect the towns of Melbourne,
Sydney, Adelaide, and Geelong	Sydney, Adelaide, and Geelong.	Sydney, Adelaide, and Geelong
Uniformity of guago bttween the colonie« ii conse-	Uniformity of guage between the colonies is conse-	Uniformity of gauge between the colonies is consequently
quently felt kyour Sydney neighbors to bt to essential,	quently felt by our Sydney neighbors to be so essential,	felt by our Sydney neighbors to be to essential,
that deip.ttches have been addressed to th« Government*	that despatches have been addressed to the Governments	that despatches have been addressed to the Government
of Victoria and South Australia, praying for their co-	of Victoria and South Australia, praying for their co-	of Victoria and South Australia, praying for their co-operation
operation in the adoption of one uniform guago. Thal	operation in the adoption of one uniform guage. That	in the adoption of one uniform gauge. That
to which thty give tht -weight of their lupport ii the	to which they give the weight of their support is the	to which they give the weight of their support in the
" narrow" gua««. I 'hink, Sir, that, If thli be adopted,	" narrow" guage. I think, Sir, that, if this be adopted,	" narrow" guard. I 'think, Sir, that, If this be adopted,
th« choice li one which Ute colonists will never cctse to	the choice is one which the colonists will never cease to	the choice li one which the colonists will never cease to
rue. The great majority of scientific men concur In	rue. The great majority of scientific men concur in	rise. The great majority of scientific men concur in
the cplnlon, that a «peed which may be maintained with	the opinion, that a speed which may be maintained with	the opinion, that a speed which may be maintained with
perfect safety upon th« " broad" «sage, would te Inad	perfect safety upon the " broad" guage, would be inad-	perfect safety upon the " broad" gauge, would be Inad
missable with the narrow.	missable with the narrow.	missable with the narrow.
Tliat lyitem which ihall with security give ui the	That system which shall with security give us the	That system which deals with security give us the
minimum of «peed, I» th» one for these colonies.	maximum of speed, is the one for these colonies.	minimum of speed, is the one for these colonies.
Raise your voice, Mr. Editor, aad u»lst in muring	Raise your voice, Mr. Editor, and assist in securing	Raise your voice, Mr. Editor, and assist in mining
for ni th« two vital ttstntlali of railway travelling	for us the two vital essentials of railway travelling—	for in the two vital essentials of railway travelling
tpeed and tecurlty. Thl» li not a question that concerní	speed and security. This is not a question that concerns	speed and security. This is not a question that concerns
ourielvei alone, bat th* who)», future of the Australian	ourselves alone, but the whole future of the Australian	ourselves alone, but the whole, future of the Australian
colonies.	colonies.	colonies.
BE WISE IN TIME.	BE WISE IN TIME.	BE WISE IN TIME.
Melbourne, September 3rd.	Melbourne, September 3rd.	Melbourne, September 3rd.

Identified overProof corrections	ESSENTIALS OURSELVES BETWEEN THEY WHEN DISTANT THINK INTHE OUR AS DESPATCHES CONCERNS SYSTEMS PRESENT BUT CEASE VAST POWER PERHAPS WHOLE SYSTEM SPEED SUPPORT FURNISH SEVERAL US THIS TOWNS ASSIST SOME OPINION
Identified overProof non-corrections	GUAGE MAXIMUM SECURING SO RUE [**VANDALISED] GOVERNMENTS INADMISSABLE CORRESPONDENTS SHALL

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	262	68.3	92.7	77.1
Searchability of unique words	143	72.7	93.7	76.9
Weighted Words		72.9	93.5	75.8

Article ID 61325796, Article, LEGISLATIVE COUNCIL BUSINESS OF TO-DAY. GOVERNMENT BUSINESS. ORDERS OF THE DAY., page 2 1853-07-06, Empire (Sydney, NSW : 1850 - 1875), 78 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
LEOlSIiATIVE COUNCIL J1USINKSS OF TO-DAY.	LEGISLATIVE COUNCIL BUSINESS OF TO-DAY.	LEGISLATIVE COUNCIL BUSINESS OF TO-DAY.
I GOVEJINMENT ])US1»£SH.	GOVERNMENT BUSINESS.	I GOVEJINMENT ])US1»£SH.
onmiis or TIIK PAY.	ORDERS OF THE DAY.	armies or THIS DAY.
ClijUjw of Hallway 1JU1 ¡ to bo further conrtilorcu in Com	Gauge of Railway Bill ; to be further considered in Committee.	ClijUjw of Railway 1901 is to be further considered in Com
Hiiril Labour lilli ; second rciidlnc;.	Hard Labour Bill ; second reading.	Hard Labour Bill ; second reading;.
Eitlinato« of Kx]iencllturo for 185U-4 ¡ toto further con	Estimates of Expenditure for 1853-4 : to be further	Estimates of Kx]iencllturo for 1893-4 a toto further con-
slüoroU lu Committee.	considered in Committee.	shares in Committee.
! (iTUEn DUSINEBS.	OTHER BUSINESS.	! (iTUEn BUSINESS.
NOTIOKS or »IOTIO.V.	NOTICES of MOTION.	NOTICES OF MOTION.
Str. Tlimttow tn move, tliat tho Volitions prraontcd by,	Mr. Thurlow to move, that the Petitions presented by	Sir. Tlimttow to move, that the Petitions presented by,
bini yojtunluy, praying tho abolition of tho Molli Licence	him yesterday, praying the abolition of the Gold Licence	him yesterday, praying the abolition of the Molly licence-fee
1'eo, ho referred to tliu Belcct Couiuilttea ou tim CloUl	Fee, be referred to the Select Committee on the Gold	he referred to the Select Committee on the Coal
rielas ¿raiiagciucut HUI.	Fields Management Bill.	Fields ¿raiiagciucut HUI.

Identified overProof corrections	YESTERDAY CONSIDERED BILL FIELDS PETITIONS RAILWAY BE THE MOTION READING PRESENTED FEE HIM SELECT LEGISLATIVE THAT BUSINESS ESTIMATES HARD NOTICES ON
Identified overProof non-corrections	EXPENDITURE GOLD OTHER GOVERNMENT ORDERS MR THURLOW GAUGE MANAGEMENT

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	72	31.9	73.6	61.2
Searchability of unique words	47	36.2	80.9	70.0
Weighted Words		32.6	80.8	71.5

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	577	66.5	91.3	74.0
Searchability of unique words	342	69.0	92.1	74.5
Weighted Words		68.9	91.9	73.9

NLA Trial Articles from 1853

Article ID 672786, Family Notices, Family Notices, page 3 1853-09-14, The Maitland Mercury and Hunter River General Advertiser (NSW : 1843 - 1893), 115 words, 4 corrections

Article ID 3714424, Family Notices, Family Notices, page 3 1853-06-04, The Moreton Bay Courier (Brisbane, Qld. : 1846 - 1861), 84 words, 4 corrections

Article ID 4788777, Family Notices, Family Notices, page 4 1853-01-07, The Argus (Melbourne, Vic. : 1848 - 1957), 82 words, 3 corrections

Article ID 4796712, Article, THE IRON ROADS OF AUSTRALIA. To the Editor of the Argus., page 5 1853-09-07, The Argus (Melbourne, Vic. : 1848 - 1957), 273 words, 9 corrections

Article ID 61325796, Article, LEGISLATIVE COUNCIL BUSINESS OF TO-DAY. GOVERNMENT BUSINESS. ORDERS OF THE DAY., page 2 1853-07-06, Empire (Sydney, NSW : 1850 - 1875), 78 words, 3 corrections

Accumulated stats for 5 articles from year 1853

Raw OCR	Human Corrected	overProof Corrected
Births.	Births.	Births.
At Armidale, on the 23th August, 1S53, tho	At Armidale, on the 23th August, 1853, the	At Armidale, on the 23th August, 1853, the
wife of Mr. Alan M'Dminld, ol a son.	wife of Mr. Alan McDonald, of a son.	wife of Mr. Alan McDonald, of a son.
At her residence, High street, West Muitland,	At her residence, High street, West Maitland,	At her residence, High street, West Maitland,
on the 9th instant, Mrs. George Norrie, of a	on the 9th instant, Mrs. George Norrie, of a	on the 9th instant, Mrs. George Norrie, of a
son.	son.	son.
Deaths.	Deaths.	Deaths.
At Oakhampton, on the 8th ins'ant, of hoop-	At Oakhampton, on the 8th instant, of hoop-	At Oakhampton, on the 8th instant, of hoop-
ing cough and influenza combined, Vranees Eliza,	ing cough and influenza combined, Frances Eliza,	ing cough and influenza combined, Frances Eliza,
a«ed two years and ten m tilths, second daughter	aged two years and ten months, second daughter	aged two years and ten m truths, second daughter
of John Clmle, E»q , of Glen Arm.	of John Clode, Esq., of Glen Arm.	of John Clarke, Esq , of Glen Arm.
On the 9th instant, at Muswellbrook, after a	On the 9th instant, at Muswellbrook, after a	On the 9th instant, at Muswellbrook, after a
protracted illness of twelvemonths, Mr. John	protracted illness of twelve months, Mr. John	protracted illness of twelve months, Mr. John
Tuckey, aged 55 years.	Tuckey, aged 55 years.	Tuckey, aged 55 years.
At his residence, Devonshire-street, West	At his residence, Devonshire-street, West	At his residence, Devonshire-street, West
Maitland, Mr. Francis Rogan, aged 40 years,	Maitland, Mr. Francis Rogan, aged 40 years,	Maitland, Mr. Francis Rogan, aged 40 years,
leaving an affectionate wife and one child to	leaving an affectionate wife and one child to	leaving an affectionate wife and one child to
lament their loss, and respected by all who	lament their loss, and respected by all who	lament their loss, and respected by all who
knew bim.	knew him.	knew him.