Classification and Generation of Derivational Morpho-semantic Relations for Polish Language

In this article, we take a new look on automated analysis and recognition of morpho-semantic relations in Polish. We present a combination of two methods for join exploration on word-form information - generating new forms and classifying pairs of words in derivational relations. As a method of generation, we used the Transformer architecture in the seq-2-seq task. Classification is performed using a neural network and using the fastText representation method. At the very end, we discussed the results obtained in the experiments.