concept linguistic feature in category nlp
appears as: linguistic features, linguistic features

This is an excerpt from Manning's book Getting Started with Natural Language Processing.
With spaCy, you can extract final three letters of a word, called suffixes in spaCy – this is one of the linguistic features of a token that we stored at the previous step. Let’s use suffixes as features. To make our feature space more compact, let’s focus on the distribution of the most frequent n% of the suffixes in our data. You can select your own cutoff point, as the code in Listing 6.11 suggests. Here, we are using 40% most frequent suffixes from the data: