def train(self, graphs):
"""
Trains a ProbabilisticDependencyGrammar based on the list of input
DependencyGraphs. This model is an implementation of Eisner's (1996)
Model C, which derives its statistics from head-word, head-tag,
child-word, and child-tag relationships.
:param graphs: A list of dependency graphs to train from.
:type: list(DependencyGraph)
"""
productions = []
events = defaultdict(int)
tags = {}
for dg in graphs:
for node_index in range(1, len(dg.nodes)):
children = dg.nodes[node_index]['deps']
nr_left_children = dg.left_children(node_index)
nr_right_children = dg.right_children(node_index)
nr_children = nr_left_children + nr_right_children
for child_index in range(0 - (nr_left_children + 1), nr_right_children + 2):
head_word = dg.nodes[node_index]['word']
head_tag = dg.nodes[node_index]['tag']
if head_word in tags:
tags[head_word].add(head_tag)
else:
tags[head_word] = set([head_tag])
child = 'STOP'
child_tag = 'STOP'
prev_word = 'START'
prev_tag = 'START'
if child_index < 0:
array_index = child_index + nr_left_children
if array_index >= 0:
child = dg.nodes[children[array_index]]['word']
child_tag = dg.nodes[children[array_index]]['tag']
if child_index != -1:
prev_word = dg.nodes[children[array_index + 1]]['word']
prev_tag = dg.nodes[children[array_index + 1]]['tag']
if child != 'STOP':
productions.append(DependencyProduction(head_word, [child]))
head_event = '(head (%s %s) (mods (%s, %s, %s) left))' % (child, child_tag, prev_tag, head_word, head_tag)
mod_event = '(mods (%s, %s, %s) left))' % (prev_tag, head_word, head_tag)
events[head_event] += 1
events[mod_event] += 1
elif child_index > 0:
array_index = child_index + nr_left_children - 1
if array_index < nr_children:
child = dg.nodes[children[array_index]]['word']
child_tag = dg.nodes[children[array_index]]['tag']
if child_index != 1:
prev_word = dg.nodes[children[array_index - 1]]['word']
prev_tag = dg.nodes[children[array_index - 1]]['tag']
if child != 'STOP':
productions.append(DependencyProduction(head_word, [child]))
head_event = '(head (%s %s) (mods (%s, %s, %s) right))' % (child, child_tag, prev_tag, head_word, head_tag)
mod_event = '(mods (%s, %s, %s) right))' % (prev_tag, head_word, head_tag)
events[head_event] += 1
events[mod_event] += 1
self._grammar = ProbabilisticDependencyGrammar(productions, events, tags)
def train(self, graphs):
"""
Trains a ProbabilisticDependencyGrammar based on the list of input
DependencyGraphs. This model is an implementation of Eisner's (1996)
Model C, which derives its statistics from head-word, head-tag,
child-word, and child-tag relationships.
:param graphs: A list of dependency graphs to train from.
:type: list(DependencyGraph)
"""
productions = []
events = defaultdict(int)
tags = {}
for dg in graphs:
for node_index in range(1, len(dg.nodes)):
# children = dg.nodes[node_index]['deps']
children = list(
chain.from_iterable(dg.nodes[node_index]["deps"].values())
)
nr_left_children = dg.left_children(node_index)
nr_right_children = dg.right_children(node_index)
nr_children = nr_left_children + nr_right_children
for child_index in range(
0 - (nr_left_children + 1), nr_right_children + 2
):
head_word = dg.nodes[node_index]["word"]
head_tag = dg.nodes[node_index]["tag"]
if head_word in tags:
tags[head_word].add(head_tag)
else:
tags[head_word] = {head_tag}
child = "STOP"
child_tag = "STOP"
prev_word = "START"
prev_tag = "START"
if child_index < 0:
array_index = child_index + nr_left_children
if array_index >= 0:
child = dg.nodes[children[array_index]]["word"]
child_tag = dg.nodes[children[array_index]]["tag"]
if child_index != -1:
prev_word = dg.nodes[children[array_index + 1]]["word"]
prev_tag = dg.nodes[children[array_index + 1]]["tag"]
if child != "STOP":
productions.append(DependencyProduction(head_word, [child]))
head_event = "(head ({} {}) (mods ({}, {}, {}) left))".format(
child,
child_tag,
prev_tag,
head_word,
head_tag,
)
mod_event = "(mods ({}, {}, {}) left))".format(
prev_tag,
head_word,
head_tag,
)
events[head_event] += 1
events[mod_event] += 1
elif child_index > 0:
array_index = child_index + nr_left_children - 1
if array_index < nr_children:
child = dg.nodes[children[array_index]]["word"]
child_tag = dg.nodes[children[array_index]]["tag"]
if child_index != 1:
prev_word = dg.nodes[children[array_index - 1]]["word"]
prev_tag = dg.nodes[children[array_index - 1]]["tag"]
if child != "STOP":
productions.append(DependencyProduction(head_word, [child]))
head_event = "(head ({} {}) (mods ({}, {}, {}) right))".format(
child,
child_tag,
prev_tag,
head_word,
head_tag,
)
mod_event = "(mods ({}, {}, {}) right))".format(
prev_tag,
head_word,
head_tag,
)
events[head_event] += 1
events[mod_event] += 1
self._grammar = ProbabilisticDependencyGrammar(productions, events, tags)