Reproducing Czech Syntactic Parsing Results Published In Conll Tasks

In this paper, I describe the approach on reproducing MST Parser and MaltParser results for Czech dependency parsing which were published in several tasks of Conference on Computational Natural Language Learning. Firstly, I briefly describe basic principles of parsers. Then, I include features and options that need to be optimized while using the parsers to get the desired results on testing files as well as evaluation methodology used in my research. I also shortly mention hardware requirements for those, who would like to train their own model for Czech language parsing. Finally, I include the practical application of trained models for our approach.