def build_tree(score, bptr, tag2idx, idx2tag, leaves):
start_id = tag2idx['S']
begin = 0
end = len(bptr) - 1
tree = build_tree_util(start_id, begin, end, bptr, tag2idx, idx2tag,
leaves)
ttf.un_chomsky_normal_form(tree)
return tree
def demo():
"""
A demonstration showing how each tree transform can be used.
"""
from copy import deepcopy
from nltk import tree, treetransforms
from nltk.draw.tree import draw_trees
# original tree from WSJ bracketed text
sentence = """(TOP
(S
(S
(VP
(VBN Turned)
(ADVP (RB loose))
(PP
(IN in)
(NP
(NP (NNP Shane) (NNP Longman) (POS 's))
(NN trading)
(NN room)))))
(, ,)
(NP (DT the) (NN yuppie) (NNS dealers))
(VP (AUX do) (NP (NP (RB little)) (ADJP (RB right))))
(. .)))"""
t = tree.Tree.fromstring(sentence, remove_empty_top_bracketing=True)
# collapse subtrees with only one child
collapsedTree = deepcopy(t)
treetransforms.collapse_unary(collapsedTree)
# convert the tree to CNF
cnfTree = deepcopy(collapsedTree)
treetransforms.chomsky_normal_form(cnfTree)
# convert the tree to CNF with parent annotation (one level) and horizontal smoothing of order two
parentTree = deepcopy(collapsedTree)
treetransforms.chomsky_normal_form(parentTree, horzMarkov=2, vertMarkov=1)
# convert the tree back to its original form (used to make CYK results comparable)
original = deepcopy(parentTree)
treetransforms.un_chomsky_normal_form(original)
# convert tree back to bracketed text
sentence2 = original.pprint()
print(sentence)
print(sentence2)
print("Sentences the same? ", sentence == sentence2)
draw_trees(t, collapsedTree, cnfTree, parentTree, original)
def demo():
"""
A demonstration showing how each tree transform can be used.
"""
from nltk.draw.tree import draw_trees
from nltk import tree, treetransforms
from copy import deepcopy
# original tree from WSJ bracketed text
sentence = """(TOP
(S
(S
(VP
(VBN Turned)
(ADVP (RB loose))
(PP
(IN in)
(NP
(NP (NNP Shane) (NNP Longman) (POS 's))
(NN trading)
(NN room)))))
(, ,)
(NP (DT the) (NN yuppie) (NNS dealers))
(VP (AUX do) (NP (NP (RB little)) (ADJP (RB right))))
(. .)))"""
t = tree.Tree.parse(sentence, remove_empty_top_bracketing=True)
# collapse subtrees with only one child
collapsedTree = deepcopy(t)
treetransforms.collapse_unary(collapsedTree)
# convert the tree to CNF
cnfTree = deepcopy(collapsedTree)
treetransforms.chomsky_normal_form(cnfTree)
# convert the tree to CNF with parent annotation (one level) and horizontal smoothing of order two
parentTree = deepcopy(collapsedTree)
treetransforms.chomsky_normal_form(parentTree, horzMarkov=2, vertMarkov=1)
# convert the tree back to its original form (used to make CYK results comparable)
original = deepcopy(parentTree)
treetransforms.un_chomsky_normal_form(original)
# convert tree back to bracketed text
sentence2 = original.pprint()
print sentence
print sentence2
print "Sentences the same? ", sentence == sentence2
draw_trees(t, collapsedTree, cnfTree, parentTree, original)
def un_cnf(tree, old_grammar):
reinsert_unary_chains(tree, old_grammar)
treetransforms.un_chomsky_normal_form(tree)
nodeList = [(tree, [])]
while nodeList != []:
node, parent = nodeList.pop()
if isinstance(node, Tree):
if '$' in node.label():
nodeIndex = parent.index(node)
parent.remove(parent[nodeIndex])
parent.insert(nodeIndex, node[0])
else:
for child in node:
nodeList.append((child, node))
def un_cnf(tree, old_grammar):
"""Convert back to the original grammar
To convert a tree output from CKY back to the original form of the grammar:
`un_cnf(tree, cnf_grammar_wunaries)`
"""
reinsert_unary_chains(tree, old_grammar)
treetransforms.un_chomsky_normal_form(tree)
nodeList = [(tree, [])]
while nodeList != []:
node, parent = nodeList.pop()
if isinstance(node, Tree):
if '$' in node.label():
nodeIndex = parent.index(node)
parent.remove(parent[nodeIndex])
parent.insert(nodeIndex, node[0])
else:
for child in node:
nodeList.append((child, node))