We can split NP non-terminals into two versions: one for subjects, and one for objects. Having two nodes ($NP_{subject}$ and $NP_{object}$) allows us to correctly model their different distributional properties since we can have different probabilities for the rules $NP_{subject} \to PRP$ and $NP_{object} \to PRP$. The intuition of splits can be implemented by doing parent annotation, in which we annotate each node with its parent in the parse tree. A PCFG can also be improved by splitting pre-terminal POS nodes, as adding specific tags for parts of speech improves PCFG modeling.