Parsing a natural language with its substantial structural complexity and ambiguity has turned out to be a puzzler. While the most of attempts in this area so far has relied on hand-generated parsers, difficulties inherent in the manual construction of natural language grammar lead up to efforts to induce the grammar automatically. Our approach to the automatic grammar induction presented in this paper has resulted in design and implementation of the system GRIND (Grammar Induction), which is capable to learn a sequence of context- -dependent parse actions from a given corpus of labelled derivation trees. To this end, GRIND combines two established methods of machine learning: transformation-based learning (TBL) and inductive logic programming (ILP). Being trained and tested on corpus SUSANNE, GRIND reached the accuracy of 96 % and the recall of 68 %. Keywords: grammar induction, inductive logic programming, transformation- -based learning 1