Words feature describe different attributes of the words present in the buffer or in the stack.
They are composed of an *address function* identifying a particular word and an *attribute function* selecting a specific attribute of the word, such as its form, lemma, part of speech ...
Such features are represented as strings that are the concatenation of the address function and the attribute function.
Such features are represented as strings that are the concatenation of the address function and the attribute function. The feature **s0f** for example corresponds to the form of the word which is on the top of the stack.
