def rnnFromTree(tree, vocabulary, wordReduction=False, grammarBased=False):
if tree.height() > 2:
if grammarBased:
cat = tree.label() + ' -> ' + ' '.join(
[child.label() for child in tree])
else:
cat = 'composition'
children = [
rnnFromTree(child, vocabulary, wordReduction) for child in tree
]
return NN.Node(children, cat, 'tanh')
else: #preterminal node
words = tree.leaves()
if len(words) == 1: word = words[0]
else: 'Not exactly one leaf?!', tree
try:
index = vocabulary.index(word)
except:
index = 0
leaf = NN.Leaf('wordIM', index, word)
if wordReduction:
# wordReduction adds an extra layer to reduce high-dimensional words
# to the dimensionality of the inner representations
if grammarBased: cat = tree.label()
else: cat = 'preterminal'
return NN.Node([leaf], cat, 'tanh')
else:
return leaf
def __init__(self, children, labels, fixed):
# print 'CLassifier.init', children
if fixed:
children = [NN.Leaf([], ('word', ), i) for i in range(children)]
comparison = NN.Node(children, [self], ('comparison', ), 'ReLU')
# leafs = [NN.Leaf([comparison],('word',),i) for i in range(n)]
# comparison.inputs=leafs
NN.Node.__init__(self, [comparison], [], ('classify', ), 'softmax')
self.labels = labels
