def binarize(cls, tree):
# collapse
t = Tree.fromstring(tree)
# chomsky normal form transformation
Tree.collapse_unary(t, collapsePOS=True, collapseRoot=True)
Tree.chomsky_normal_form(t)
s = cls._format(t)
return s
def collectSymbols(sample, cnf=False):
def dfs(root, sample):
if root not in sample:
return Tree(root, [])
else:
return Tree(root, [dfs(child, sample) for child in sample[root]])
tree = dfs("ROOT", sample)
if cnf:
Tree.chomsky_normal_form(tree)
out = set()
for production in tree.productions():
lhs, rhs = production.lhs(), production.rhs()
if rhs:
for nonterminal in rhs:
out.add(re.sub(r"-\d+", '', nonterminal.symbol()))
return out
def extract_CNF_rules(self):
for i in range(len(self.all_lines)):
t = Tree.fromstring(self.all_lines[i])
Tree.chomsky_normal_form(t)
self.CNF_rules += t.productions()
def __binarize__(const_t_nltk: Tree):
# chomsky normal form transformation
Tree.chomsky_normal_form(const_t_nltk)
