- From: Lisa Seeman <seeman@netvision.net.il>
- Date: Sun, 18 Aug 2002 17:26:22 -0700
- To: "W3c-Wai-Gl@W3.Org (E-mail)" <w3c-wai-gl@w3.org>
Received on Sunday, 18 August 2002 10:26:24 UTC
More interestly perhapes is some resurch being done at the Technion. The Technoin in Haifa is an engineering biased university that I would recommend as world class. They have been working on this issue, and I am sending a URL for an English abstract of the work. http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud.html#English The impression I get is, well, mixed There is some progress, in at least it is being addressed, but as quoted from the abstract "Due to the rich morphology of the Hebrew language and the inadequacy of the undotted script which results in a great degree of morphological ambiguity, the problem has not yet found a satisfactory solution. " However they then claimed to have achieved 96% success, except that they were using a dictionary of only 5000 words - so each spelling could not have had many options. I have contacted the researcher, and hope to have more information soon. All the best, Lisa Seeman UnBounded Access Widen the World Web http://www.UBaccess.com
Received on Sunday, 18 August 2002 10:26:24 UTC