Other formats:
BibTeX
LaTeX
RIS
@misc{359151, author = {Smrž, Pavel and Sojka, Petr}, keywords = {neural networks;hyphenation}, language = {eng}, title = {Word Hy-phen-a-tion by Neural Networks}, url = {http://www.fi.muni.cz/reports/1996/full.shtml}, year = {1996} }
TY - GEN ID - 359151 AU - Smrž, Pavel - Sojka, Petr PY - 1996 TI - Word Hy-phen-a-tion by Neural Networks VL - FIMU-RS-96-04 KW - neural networks;hyphenation UR - http://www.fi.muni.cz/reports/1996/full.shtml L2 - http://www.fi.muni.cz/reports/1996/full.shtml N2 - 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. ER -
SMRŽ, Pavel and Petr SOJKA. \textit{Word Hy-phen-a-tion by Neural Networks}. 1996. FIMU-RS-96-04.
|