def ids_to_tree(self, emb, postprocess=True):
"""Create a fake (flat) t-tree from token embeddings (IDs).
@param emb: source embeddings (token IDs)
@param postprocess: postprocess the sentence (capitalize sentence start, merge plural \
markers)? True by default.
@return: the corresponding tree
"""
tree = TreeData()
tokens = self.ids_to_strings(emb)
for token in tokens:
if token in ['<GO>', '<STOP>', '<VOID>']:
continue
if postprocess:
# casing (only if set to lowercase)
if self.lowercase and len(tree) == 1 or tree.nodes[-1].t_lemma in ['.', '?', '!']:
token = token[0].upper() + token[1:]
# plural merging (if plural tokens come up)
if token == '<-s>' and tree.nodes[-1].t_lemma is not None:
token = self._singular_to_plural(tree.nodes[-1].t_lemma)
tree.remove_node(len(tree) - 1)
elif token == '<-s>':
continue
tree.create_child(0, len(tree), NodeData(token, 'x'))
return tree
def ids_to_tree(self, emb, postprocess=True):
"""Create a fake (flat) t-tree from token embeddings (IDs).
@param emb: source embeddings (token IDs)
@param postprocess: postprocess the sentence (capitalize sentence start, merge plural \
markers)? True by default.
@return: the corresponding tree
"""
tree = TreeData()
tokens = self.ids_to_strings(emb)
for token in tokens:
if token in ['<GO>', '<STOP>', '<VOID>']:
continue
if postprocess:
# casing (only if set to lowercase)
if self.lowercase and len(tree) == 1 or tree.nodes[-1].t_lemma in ['.', '?', '!']:
token = token[0].upper() + token[1:]
# plural merging (if plural tokens come up)
if token == '<-s>' and tree.nodes[-1].t_lemma is not None:
token = self._singular_to_plural(tree.nodes[-1].t_lemma)
tree.remove_node(len(tree) - 1)
elif token == '<-s>':
continue
tree.create_child(0, len(tree), NodeData(token, 'x'))
return tree
