def clean_instance(instance):
'''
Gets an instance ready for feature extraction.
'''
try:
# make instance's tree a real tree
tree_text = APBTree.fix_parse_tree_text(instance.tree, instance.pos)
instance = instance._replace(tree=APBTree.APBTree(tree_text))
# get arguments into useable form
arguments = []
Argument = namedtuple('Argument', 'label position text description')
for (label, arg) in instance.arguments.items():
text = arg[0] if '-NONE-' not in arg[0] else arg[0].split()[1]
argument = Argument(
label=label,
text=text,
description=arg[1],
position=instance.tree.get_arg_node_position(text))
arguments.append(argument)
instance = instance._replace(arguments=arguments)
# fix up predicate
Predicate = namedtuple('Predicate', 'text position')
position = instance.tree.get_predicate_node_position(
instance.predicate, instance.pos)
predicate = Predicate(text=instance.predicate, position=position)
instance = instance._replace(predicate=predicate)
except:
return None
return instance
def clean_instance(instance):
'''
Gets an instance ready for feature extraction.
'''
try:
# make instance's tree a real tree
tree_text = APBTree.fix_parse_tree_text(instance.tree, instance.pos)
instance = instance._replace(tree=APBTree.APBTree(tree_text))
# get arguments into useable form
arguments = []
Argument = namedtuple('Argument', 'label position text description')
for (label, arg) in instance.arguments.items():
text = arg[0] if '-NONE-' not in arg[0] else arg[0].split()[1]
argument = Argument(label=label,
text=text,
description=arg[1],
position=instance.tree.get_arg_node_position(text))
arguments.append(argument)
instance = instance._replace(arguments=arguments)
# fix up predicate
Predicate = namedtuple('Predicate', 'text position')
position = instance.tree.get_predicate_node_position(instance.predicate, instance.pos)
predicate = Predicate(text=instance.predicate, position=position)
instance = instance._replace(predicate=predicate)
except:
return None
return instance
def __init__(self, tree, sense_gloss, arguments, roleset, pos):
self.filename = 'file.name'
'''Name of the Arabic TreeBank file containing the parse tree'''
self.sentnum = sentnum
"""The sentence number of this sentence within ``fileid``.
Indexing starts from zero."""
self.wordnum = wordnum
"""The word number of this instance's predicate within its
containing sentence. Word numbers are indexed starting from
zero, and include traces and other empty parse elements."""
self.tagger = 'gold'
"""An identifier for the tagger who tagged this instance; or
``'gold'`` if this is an adjuticated instance."""
self.roleset = roleset
"""The name of the roleset used by this instance's predicate.
Use ``propbank.roleset() <PropbankCorpusReader.roleset>`` to
look up information about the roleset."""
self.inflection = None #inflection
"""A ``PropbankInflection`` object describing the inflection of
this instance's predicate."""
self.predicate = predicate
"""A ``PropbankTreePointer`` indicating the position of this
instance's predicate within its containing sentence."""
self.arguments = tuple(arguments)
"""A list of tuples (argloc, argid), specifying the location
and identifier for each of the predicate's argument in the
containing sentence. Argument identifiers are strings such as
``'ARG0'`` or ``'ARGM-TMP'``. This list does *not* contain
the predicate."""
self.sense_gloss = sense_gloss
# make instance's tree a real tree
try:
tree_text = APBTree.fix_parse_tree_text(tree, pos)
self.tree = APBTree.APBTree(tree_text)
except:
self.tree = None
def __init__(self, tree, sense_gloss, arguments, roleset, pos):
self.filename = 'file.name'
'''Name of the Arabic TreeBank file containing the parse tree'''
self.sentnum = sentnum
"""The sentence number of this sentence within ``fileid``.
Indexing starts from zero."""
self.wordnum = wordnum
"""The word number of this instance's predicate within its
containing sentence. Word numbers are indexed starting from
zero, and include traces and other empty parse elements."""
self.tagger = 'gold'
"""An identifier for the tagger who tagged this instance; or
``'gold'`` if this is an adjuticated instance."""
self.roleset = roleset
"""The name of the roleset used by this instance's predicate.
Use ``propbank.roleset() <PropbankCorpusReader.roleset>`` to
look up information about the roleset."""
self.inflection = None #inflection
"""A ``PropbankInflection`` object describing the inflection of
this instance's predicate."""
self.predicate = predicate
"""A ``PropbankTreePointer`` indicating the position of this
instance's predicate within its containing sentence."""
self.arguments = tuple(arguments)
"""A list of tuples (argloc, argid), specifying the location
and identifier for each of the predicate's argument in the
containing sentence. Argument identifiers are strings such as
``'ARG0'`` or ``'ARGM-TMP'``. This list does *not* contain
the predicate."""
self.sense_gloss = sense_gloss
# make instance's tree a real tree
try:
tree_text = APBTree.fix_parse_tree_text(tree, pos)
self.tree = APBTree.APBTree(tree_text)
except:
self.tree = None