论文信息 - The complex of neural networks and probabilistic methods for mathematical modeling of the syntactic structure of a sentence of natural language

The complex of neural networks and probabilistic methods for mathematical modeling of the syntactic structure of a sentence of natural language

The formalized model to construct the syntactic structure of sentences of a natural language is presented. On base of this model the complex algorithm with use of neural networks founded on data of Russian National language Corpus and set of parameters extracted from this data was developed. The resulted accuracy along with possible accuracy which theoretically could be received with these parameters is presented.

[1] Chun Kit Wong. Recursive auto-associative memory as connectionist language processing model : training improvements via hybrid neural-genetic schemata , 2004 .

[2] Geoffrey E. Hinton,et al. Deep Learning , 2015, Nature.

[3] Yoshua Bengio,et al. A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[4] Ameet Talwalkar,et al. Ensemble Nystrom Method , 2009, NIPS.

[5] Joakim Nivre,et al. Incrementality in Deterministic Dependency Parsing , 2004 .

[6] Danqi Chen,et al. A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[7] Tong Zhang,et al. Solving large scale linear prediction problems using stochastic gradient descent algorithms , 2004, ICML.

[8] Anderson Rocha,et al. Multiclass From Binary: Expanding One-Versus-All, One-Versus-One and ECOC-Based Approaches , 2014, IEEE Transactions on Neural Networks and Learning Systems.