The model of Russian language parser based on a combination of neural networks along with extraction of set of parameters which allows to establish relations with the minimal syntactic ambiguity is presented. The parse tree of sentence is constructed in the format of Russian National Corpus (RNC). RNC texts containing morphological and syntactic markup are used for training neural network models as part of procedure. Estimates of accuracy of the developed parser procedure in comparison with the other Russian language parser systems have been performed.
展开▼
