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 105895070, Article, Society Meeting Called, page 26 1961-09-27, The Canberra Times (ACT : 1926 - 1995), 136 words, 3 corrections

Raw OCR	Human Corrected	overProof Corrected
Society?	Society	Society?
Meetiml	Meeting	Meeting
Called i	Called	Called A
A special general	A special general	special general
\| meeting of the Canberra	meeting of the Canberra	meeting of the Canberra
l Co - operative Society	Co-operative Society	l Co - operative Society
will be held on October	will be held on October	will be held on October
9.	9.	9.
The Registrar of Co-opera,	The Registrar of Co-opera-	The Registrar of Co-operative
tive Sovieties, Mr. J. D. But*	tive Societies, Mr. J. D. But-	Societies, Mr. J. D. Butt
ton, has called the meeting,	ton, has called the meeting.	ton, has called the meeting,
The meeting, for share	The meeting, for share-	The meeting, for shareholders
holders only, will be closed	holders only, will be closed	only, will be closed
to the Press and the public,	to the Press and the public.	to the Press and the public,
Shareholders will hear Hit	Shareholders will hear the	Shareholders will hear the
result of an inspectoi'i	result of an inspector's	result of an inspector's
inquiry into the society's	inquiry into the society's	inquiry into the society's
affairs.	affairs.	affairs.
The society's board ot	The society's board of	The society's board of
directors requested : tit	directors requested the	directors requested : the
inquiry on May 23.	inquiry on May 23.	inquiry on May 23.
Mr. Button appointed Mr.	Mr. Button appointed Mr.	Mr. Button appointed Mr.
Keith Bennetts to examine	Keith Bennetts to examine	Keith Bennetts to examine
and report on the Co-Opera	and report on the Co-Opera-	and report on the Co-Operative
tive's minutes, books, docu	tive's minutes, books, docu-	minutes, books, documents,
ments, stock, securities and	ments, stock, securities and	stock, securities and
affairs.	affairs.	affairs.
. Shareholders also will bt	Shareholders also will be	. Shareholders also will be
told what action the board ot'	told what action the board of	told what action the board of'
directors has taken or is con-'	directors has taken or is con-	directors has taken or is considering.
sidering. 1	sidering.	1
They will be required to	They will be required to	They will be required to
produce their share books at	produce their share books at	produce their share books at
the door to prove member-'	the door to prove member-	the door to prove membership
ship.	ship.

Identified overProof corrections	INSPECTORS MEMBERSHIP SOCIETIES CONSIDERING
Identified overProof non-corrections	TIVES [VANDALISED] TIVE [VANDALISED] OPERA [VANDALISED] /CO/OPERA\|COOPERA [VANDALISED]

	Word count	OCR accuracy %	overProof accuracy %	Errors corrected %
All Words	118	91.5	95.8	50.0
Searchability of unique words	71	94.4	94.4	0.0
Weighted Words		95.6	95.6	0.0

NLA Trial Articles from 1961

Article ID 105895070, Article, Society Meeting Called, page 26 1961-09-27, The Canberra Times (ACT : 1926 - 1995), 136 words, 3 corrections

Accumulated stats for 1 articles from year 1961