--0-1248790713-11964574437275 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit My work is on subsegmental primes for speech recognition and I have plans to related to text recognition. Ok, I'll be loking forward to see your work. thankx miki Miki Vz <mikisvaz / yahoo.com> wrote: al_batuul wrote: > Dear Miki, > > I am very interested in the text Mining library, please inform me when > ready, > Fatmah Its a library to process Text for Biology. I does document classification and named entity extraction and normalization, and I'm yet to port from the earlier perl version the code for protein protein interaction detection. The library is already complete, and I'm using it for some text analysis system I'm working on. It also has a complete evaluation system for each step, using PubMed articles and the Biocreative data sets, so it should be useful for other researchers on the field. I have to still publish it, I guess I need to clean and organize the code a bit, and figure out all the copyrigth stuff. But I'm really looking forward, I'd love to have some input. mail me at mikisvaz at yahoo com and i'll keep you informed. Cheers - Miki -- Posted via http://www.ruby-forum.com/. --------------------------------- Be a better sports nut! Let your teams follow you with Yahoo Mobile. Try it now. --0-1248790713-11964574437275--