NLA Trial index

NLA Trial Articles from 1847

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 12893860, Article, DEPARTURES., page 2 1847-07-13, The Sydney Morning Herald (NSW : 1842 - 1954), 76 words, 4 corrections

Raw OCRHuman CorrectedoverProof Corrected
DEPARTURES. DEPARTURES. DEPARTURES.
July 12.-Soutenir, schooner, 64 tons, Cap- July 12.—Souvenir, schooner, 64 tons, Cap- July 12 Souvenir, schooner, 64 tons, Captain
tain Jennings. Resumed her voyage for Port tain Jennings. Resumed her voyage for Port Jennings. Resumed her voyage for Port
PhiUip. Phillip. Phillip.
July 12.-Nebo», barque, 247 tons, Captain July 12.—Nelson, barque, 247 tons, Captain July 12. Nebo, barque, 247 tons, Captain
Spurling, for the South Sea Fishery. Pas- Spurling, for the South Sea Fishery. Pas- Spurling, for the South Sea Fishery. Pas-
senger-Master Spurling. senger—Master Spurling. senger Master Spurling.
July 12.-jin» ¿for), schooner, 49 tons, July 12.—Ann Mary, schooner, 49 tons, July 12-year for), schooner, 49 tons,
Captain Brown, for Moreton Bay. Pas- Captain Brown, for Moreton Bay. Pas- Captain Brown, for Moreton Bay. Pas-
sengers-Mr. and Mrs. Nowlan, and Mr. W. sengers—Mr. and Mrs. Nowlan, and Mr. W. sengers-Mr. and Mrs. Nowlan, and Mr. W.
Christie. Christie. Christie.
July 12.- Ifattiand, steamer, 103 tons, Captain July 12.—Maitland, steamer, 103 tons, Captain July 12.- Maitland, steamer, 103 tons, Captain
Parsons, for Moreton Bay. Passengers - Mr. Parsons, for Moreton Bay. Passengers — Mr. Parsons, for Moreton Bay. Passengers - Mr.
Watson, Mr. Coutts, "Mr. M'Conncll, Mr. Watson, Mr. Coutts, Mr. McConnell, Mr. Watson, Mr. Coutts, Mr. M'Connell, Mr.
Living, and six in the steerage. Living, and six in the steerage. Living, and six in the steerage.
Identified overProof corrections PHILLIP MAITLAND SOUVENIR PASSENGER
Identified overProof non-corrections ANN MCCONNELL NELSON MARY
Word
count		OCR
accuracy %		overProof
accuracy %		Errors
corrected %
All Words6885.391.240.0
Searchability of unique words4381.490.750.0
Weighted Words84.592.350.0

Article ID 36253142, Article, FROM SECOND EDITION., page 6 1847-10-09, Launceston Examiner (Tas. : 1842 - 1899), 70 words, 3 corrections

Raw OCRHuman CorrectedoverProof Corrected
SECOND EDITION. SECOND EDITION. SECOND EDITION.
TnRAnssiEN's BA.Lr. - This entertaintment TRADESMEN'S BALL.—This entertainment TnRAnssiEN's BALL. - This entertaintment
passed off exceedingly to the satisfaction of all passed off exceedingly to the satisfaction of all passed off exceedingly to the satisfaction of all
present, about two hundred and fifty. present, about two hundred and fifty. present, about two hundred and fifty.
WEDNESDAY'S MAIL.-W. P. Kay, Director WEDNESDAY'S MAIL.—W. P. Kay, Director WEDNESDAY'S MAIL W. P. Kay, Director
of Public Works, is appointed Director-General of Public Works, is appointed Director-General of Public Works, is appointed Director-General
of Roads.... A desperate attenmpt had been made of Roads. . . . A desperate attempt had been made of Roads.... A desperate attempt had been made
to rob the Derwent Bank; but without success. to rob the Derwent Bank ; but without success. to rob the Derwent Bank; but without success.
A reward orf' £100 is offered on conviction of the A reward of £100 is offered on conviction of the A reward of' £100 is offered on conviction of the
offender.... The Colonist had arrived; but not the offender. . . . The Colonist had arrived ; but not the offender.... The Colonist had arrived; but not the
Jane Frances, as reported. Jane Frances, as reported. Jane Frances, as reported.
Identified overProof corrections ATTEMPT BALL
Identified overProof non-corrections TRADESMENS ENTERTAINMENT
Word
count		OCR
accuracy %		overProof
accuracy %		Errors
corrected %
All Words6592.396.960.0
Searchability of unique words5392.596.250.0
Weighted Words92.796.350.0

Article ID 48543433, Family Notices, Family Notices, page 2 1847-01-13, South Australian Register (Adelaide, SA : 1839 - 1900), 55 words, 4 corrections

Raw OCRHuman CorrectedoverProof Corrected
BIRTHS. BIRTHS. BIRTHS.
On Thursday the 7th instant, at Pcnnington-lerrace, On Thursday the 7th instant, at Pennington-terrace, On Thursday the 7th instant, at Pennington-terrace,
North Adelaide, Mrs Henry Watson, of a son. North Adelaide, Mrs. Henry Watson, of a son. North Adelaide, Mrs Henry Watson, of a son.
On Sunday the I Oth instant, the lady of H. W. Phillips On Sunday the 10th instant, the lady of H. W. Phillips On Sunday the 10th instant, the lady of H. W. Phillips
Esq., of a sen, still bom. Esq., of a son, still born. Esq., of a son, still born.
On Sunday tho 10 instant, at Pennington-terrace, North On Sunday the 10 instant, at Pennington-terrace, North On Sunday the 10 instant, at Pennington-terrace, North
Adelaide, the lady of George Tinline, Esq., of a daughter. Adelaide, the lady of George Tinline, Esq., of a daughter. Adelaide, the lady of George Tinline, Esq., of a daughter.
Identified overProof corrections BORN
Identified overProof non-corrections
Word
count		OCR
accuracy %		overProof
accuracy %		Errors
corrected %
All Words4393.0100.0100.0
Searchability of unique words2495.8100.0100.0
Weighted Words96.4100.0100.0

Accumulated stats for 3 articles from year 1847

Word
count		OCR
accuracy %		overProof
accuracy %		Errors
corrected %
All Words17689.895.555.6
Searchability of unique words12089.295.053.7
Weighted Words90.495.754.6