An analogical proportion (AP) is a relation between four elements A, B, C, and D meaning "A is to B as C is to D", often written as A:B::C:D. For example, "cat : kitten :: dog : puppy" and "cat : cats :: dog : dogs" are two APs between words. Notice that the relation between "cat" and "kitten" is a semantic one (i.e. on the meaning: "kitten" is a young "cat") while the one between "cat" and "cats" is morphological (i.e. on the structure of the words: "cats" is the plural of "cat", obtained with the suffix "-s"), as depending on the context, APs can cover relations of different nature. In this talk, I will demonstrate how deep learning tools developed to manipulate APs between words (as in the examples above) can be used to transfer semantic labels in the frame semantic framework, and what are the pros and cons of such an approach. In particular, I will cover the notion of analogical equations, where we want to find a value x making the quadruple A:B::C:x an AP, and how to solve analogical equations for specific relations between words and between groups of words.