Chart Parsing with CKY and Neural Span Scores

Chart Parsing with CKY and Neural Span Scores

Scoring spans with a network

CKY and span scores in Python

How does conversion to Chomsky normal form handle the rule $VP \to V\ NP\ PP$, and why is the conversion safe?

In the CKY table, what does cell $[i, j]$ contain, and where does the algorithm look when filling it?

A constituent spans 5 words, from fencepost $i$ to fencepost $j$. How many split points $k$ with $i < k < j$ must CKY try when filling that cell? Answer with the number.

CKY parses a sentence of $n$ words with three nested loops, over columns, cells, and split points. For $n = 12$, how many (cell, split) combinations does the algorithm consider, ignoring the grammar? Answer with the number.

A parser's tree contains 9 constituents, the gold tree contains 10, and 8 constituents match exactly in label and span. Compute the labeled $F_1$, rounding to three decimals.