NLA Trial index

NLA Trial Articles from 1817

Notes
  1. 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.
  2. 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.
  3. 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
  4. 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.
  5. 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.
  6. 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.
  7. 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 653223, Advertising, Classified Advertising, page 2 1817-10-25, The Hobart Town Gazette and Southern Reporter (Tas. : 1816 - 1821), 106 words, 4 corrections

Raw OCRHuman CorrectedoverProof Corrected
TÄTANTED immediately, for the Brig SOPHIA, now" about to WANTED immediately, for the Brig SOPHIA, now about to WANTED immediately, for the Brig SOPHIA, now" about to
?V proceed on a Sealing Voyage, SIX FÏNE YOU.NUTABLS proceed on a Sealing Voyage, SIX FINE YOUNG ABLE V proceed on a Sealing Voyage, SIX FINE YOU.NUTABLS
BODIED SEAMEN.— Enquire of Mr. Birch, or Captain Kelly. BODIED SEAMEN.— Enquire of Mr. Birch, or Captain Kelly. BODIED SEAMEN'S Enquire of Mr. Birch, or Captain Kelly.
-------- -------- --------
TO be Sold by Private Contract, that excellent Dwelling-house, TO be Sold by Private Contract, that excellent Dwelling-house, TO be Sold by Private Contract, that excellent Dwelling-house,
lately the Residence of Mr. Lewis, in Liverpool-street, with lately the Residence of Mr. Lewis, in Liverpool-street, with lately the Residence of Mr. Lewis, in Liverpool-street, with
commodious Apartments, Stables, Çut-^ôure», and ,a;Garden-in gqod, , commodious Apartments, Stables, Out-houses, and a Garden in good commodious Apartments, Stables, pressures, and ,a;Garden-in good, ,
VP$P91* ;4tf°» ,\wo Apres of^Gxounçi^ppçil'te t]ie Premifes,, for condition ; Also two Acres of Ground opposite the Premises, for VP$P91* ;4tf°» ,\wo Apres of^Gxounçi^ppçil'te the Premises,, for
the purpofe of Building upon, this is' a delightful Situation for '' the purpose of Building upon. This is a delightful Situation for the purpose of Building upon this is a delightful Situation for ''
*W W?0 wifliiqg xp en^r into Bufinefs. Liberal Crefli>. will be . any person wishing to enter into Business. Liberal Credit will be W W?0 wishing xp enter into Business. Liberal Credit. will be
given to the Pur cha fer,' on approved Security.- 4 pply to Capta iii given to the Purchaser, on approved Security.— Apply to Captain given to the Pur chas fer,' on approved Security.- 4 apply to Capt iii
BLYTH, the Proprietor,,Kennington, ^rm, near Humphrey'* River, BLYTH, the Proprietor, Kensington Farm, near Humphrey's River. BLYTH, the Proprietor,,Kennington, arm, near Humphrey's River,
Identified overProof corrections WANTED CREDIT HUMPHREYS BUSINESS FINE GOOD PREMISES WISHING ENTER PURPOSE APPLY
Identified overProof non-corrections OPPOSITE FARM PERSON KENSINGTON SEAMEN [**VANDALISED] TWO ACRES CONDITION PURCHASER /OUT/HOUSES|OUTHOUSES ABLE ANY PROPRIETOR GARDEN GROUND ALSO YOUNG
Word
count
OCR
accuracy %
overProof
accuracy %
Errors
corrected %
All Words10168.379.234.4
Searchability of unique words8267.179.337.0
Weighted Words66.679.337.8

Article ID 2177495, Article, EXECUTION., page 2 1817-10-04, The Sydney Gazette and New South Wales Advertiser (NSW : 1803 - 1842), 123 words, 6 corrections

Raw OCRHuman CorrectedoverProof Corrected
EXEiLTioN, EXECUTION. EXEiLTioN,
Yesterday the unhappy man who was condemned for Yesterday the unhappy man who was condemned for Yesterday the unhappy man who was condemned for
the crime of wilful minder on Tuesday last, was ex- the crime of wilful murder on Tuesday last, was ex- the crime of wilful murder on Tuesday last, was executed
ecuted pursuant to his sentence, and afterwards gives ecuted pursuant to his sentence, and afterwards given pursuant to his sentence, and afterwards gives
over for dissection. A/ eight o'clock he was taken over for dissection. At eight o'clock he was taken over for dissection. At eight o'clock he was taken
from the county gaol, and expressing a desire to be per* from the county gaol, and expressing a desire to be per- from the county gaol, and expressing a desire to be permitted
nutted to walk lo the place of execution, slowly moved mitted to walk to the place of execution, slowly moved to walk to the place of execution, slowly moved
thither, attended by a numerous crowd of spectators. thither, attended by a numerous crowd of spectators. thither, attended by a numerous crowd of spectators.
We do not hear that he made any confession ; but ap« We do not hear that he made any confession ; but ap- We do not hear that he made any confession ; but appeared
peared on the contrary averse to all communication ; peared on the contrary averse to all communication ; on the contrary averse to all communication and
and it is painful to add; went out of the world without and it is painful to add, went out of the world without it is painful to add; went out of the world without
any evident situs of a sincere Conti ition <md repentance any evident signs of a sincere contrition and repentance any evident signs of a sincere Conti ition and repentance
of hi* ? ..st ert » «.. of his past errors. of his best art 6 2..
SYUNKi ; I'lU'NTJLD BY «. HOW*. ' f SYDNEY: PRINTED BY G. HOWE. SYDNEY ; I'lU'NTJLD BY G. HOWE. of
Identified overProof corrections SIGNS SYDNEY PERMITTED AT HOWE MURDER
Identified overProof non-corrections ERRORS PAST GIVEN PRINTED CONTRITION
Word
count
OCR
accuracy %
overProof
accuracy %
Errors
corrected %
All Words10786.094.460.0
Searchability of unique words8086.293.854.5
Weighted Words86.994.557.9

Accumulated stats for 2 articles from year 1817

Word
count
OCR
accuracy %
overProof
accuracy %
Errors
corrected %
All Words20877.487.042.5
Searchability of unique words16276.586.542.3
Weighted Words77.087.143.9