by Pavel Smrž, Petr Sojka, August 1996, 10 pages.
FIMU-RS-96-04. Available as Postscript, PDF.
We are discussing our experiments we made when learning feedforward neural network to find possible hyphenation points in all words of given language. Neural networks show to be a good device for solving this difficult problem. The structure of the multilayer neural network used is given, together with a discussion about training sets, influence of input coding and results of experiments done for the Czech language. We end up with pros and cons of our approach tested - hybrid architecture suitable for a multilingual system.
by Petr Sojka, August 1995, 12 pages.
FIMU-RS-95-04. Available as Postscript, PDF.
The problems of the automatic compound word and discretionary hyphenation in TeX are discussed. These hyphenation points have to be marked manually in the TeX source file so far. Several methods how to tackle with these problems are observed. The results obtained from experiments with German wordlist are discussed.