Další formáty:
BibTeX
LaTeX
RIS
@article{190170, author = {Smrž, Pavel and Sojka, Petr}, article_location = {Praha}, article_number = {6}, keywords = {hyphenation; neural networks; backpropagation}, language = {eng}, issn = {1210-0552}, journal = {Neural Network World}, title = {Word Hy-phen-ation by Neural Networks}, url = {http://nlp.fi.muni.cz/publications/nnw1997_smrz_sojka/}, volume = {7}, year = {1997} }
TY - JOUR ID - 190170 AU - Smrž, Pavel - Sojka, Petr PY - 1997 TI - Word Hy-phen-ation by Neural Networks JF - Neural Network World VL - 7 IS - 6 SP - 687 EP - 687 PB - IDG Czechoslovakia SN - 12100552 KW - hyphenation KW - neural networks KW - backpropagation UR - http://nlp.fi.muni.cz/publications/nnw1997_smrz_sojka/ 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 a Petr SOJKA. Word Hy-phen-ation by Neural Networks. \textit{Neural Network World}. Praha: IDG Czechoslovakia, 1997, roč.~7, č.~6, s.~687-695. ISSN~1210-0552.
|