>Subject: Corpora: ocr error correction
>Does anyone know about projects or people working
>with automatic correction of ocr errors?
&
On Mon, 14 Jun 1999 "Mcenery, Tony" wrote:
>Subject: Corpora of Minority Languages
>The Department of Linguistics at Lancaster is currently
>engaged in work aimed at establishing the needs of
>the language engineers and linguists with regard
>to corpus building in non-indigenous minority languages
>in Europe.
Mason Integrated Technologies Ltd (MIT2) is involved
in OCR software development for several different
French-lexicon Creole minority languages in the
United States and in various European countries.
It has also developed spelling reform/orthography
conversion software for Haitian Creole with plans
to extend this rapidly to other French creoles.
Descriptions of the CreoleScan(tm) and
CreoleConvert(tm) systems are indicated at:
Mason Integrated Technologies Ltd:
http://hometown.aol.com/mit2usa/Index2.html
Permission has been granted from owners of
various texts to make their data and the
results of the scanning and orthography
conversion software accessible for demonstration
and research purposes. Please see the
following address for this data:
Orthographically Converted Creole Texts:
http://hometown.aol.com/mit2haiti/Index4.html
Regards,
Marilyn Mason
President
*******
Mason Integrated Technologies Ltd
P.O. Box 181015
Boston, MA 02118 USA
(617) 247-8885 (office & answering machine)
(617) 262-8923 (FAX)
MIT2USA@aol.com (e-mail)
Mason Integrated Technologies Ltd Home Page:
http://hometown.aol.com/mit2usa/Index2.html
Orthographically Converted HC Texts Download Site:
http://hometown.aol.com/mit2haiti/Index4.html
Meet Marilyn Mason:
http://hometown.aol.com/marilinc/Index3.html
Seychelles Invited Seminar Pictures Page:
http://hometown.aol.com/marilinc/Index1.html