def create_instances(self, examples):
all_instances = []
succ = 0
for id, ex in enumerate(logged_loop(examples)):
n_words = len(ex['word']) - 1
# arcs = {(h, t, label)}
stack = [0]
buf = [i + 1 for i in xrange(n_words)]
arcs = []
instances = []
for i in xrange(n_words * 2):
gold_t = self.get_oracle(stack, buf, ex)
if gold_t is None:
break
legal_labels = self.legal_labels(stack, buf)
assert legal_labels[gold_t] == 1
instances.append((self.extract_features(stack, buf, arcs, ex),
legal_labels, gold_t))
if gold_t == self.n_trans - 1:
stack.append(buf[0])
buf = buf[1:]
elif gold_t < self.n_deprel:
arcs.append((stack[-1], stack[-2], gold_t))
stack = stack[:-2] + [stack[-1]]
else:
arcs.append((stack[-2], stack[-1], gold_t - self.n_deprel))
stack = stack[:-1]
else:
succ += 1
all_instances += instances
return all_instances
def create_instances(self, examples):
all_instances = []
succ = 0
for id, ex in enumerate(logged_loop(examples)):
n_words = len(ex['word']) - 1
# arcs = {(h, t, label)}
stack = [0]
buf = [i + 1 for i in xrange(n_words)]
arcs = []
instances = []
for i in xrange(n_words * 2):
gold_t = self.get_oracle(stack, buf, ex)
if gold_t is None:
break
legal_labels = self.legal_labels(stack, buf)
assert legal_labels[gold_t] == 1
instances.append(
(self.extract_features(stack, buf, arcs,
ex), legal_labels, gold_t))
if gold_t == self.n_trans - 1:
stack.append(buf[0])
buf = buf[1:]
elif gold_t < self.n_deprel:
arcs.append((stack[-1], stack[-2], gold_t))
stack = stack[:-2] + [stack[-1]]
else:
arcs.append((stack[-2], stack[-1], gold_t - self.n_deprel))
stack = stack[:-1]
else:
succ += 1
all_instances += instances
return all_instances
def create_instances(self, examples):
all_instances = []
succ = 0
for id, ex in enumerate(logged_loop(examples)):
n_words = len(ex['word']) - 1
# arcs = {(h, t, label)}
stack = [0]
# buf初始保存句子中所有的词
# 这个序号和head集合中的序号是对应的,序号范围在句子的长度内
buf = [i + 1 for i in xrange(n_words)]
arcs = []
instances = []
for i in xrange(n_words * 2):
# 总共会执行2*n_words次trans操作,n为句子中单词总数
# 得到当前状态下正确的trans操作
gold_t = self.get_oracle(stack, buf, ex)
if gold_t is None:
break
legal_labels = self.legal_labels(stack, buf)
assert legal_labels[gold_t] == 1
# 为句子的每一次状态变化创建一个状态向量实例f=[18+18+12]
# 每个状态向量表征当前未变化前的状态,对应一个正确的可执行操作的标识
# 总共有2*n_words个状态向量F
instances.append(
(self.extract_features(stack, buf, arcs,
ex), legal_labels, gold_t))
# 更新状态
if gold_t == self.n_trans - 1: # ==2 shift
stack.append(buf[0])
buf = buf[1:]
elif gold_t < self.n_deprel: # == 0 left-arc
arcs.append((stack[-1], stack[-2], gold_t))
stack = stack[:-2] + [stack[-1]] # stack去除-2元素
else: # ==1 right-arc
right_label = gold_t if self.unlabeled else gold_t - self.n_deprel
arcs.append((stack[-2], stack[-1],
right_label)) # 添加新获得的弧,(h,t)对应词序
stack = stack[:-1] # stack去除-1元素
else:
succ += 1
all_instances += instances # 将提取回的句子特征加入总特征实例集合
return all_instances
def create_instances(self, examples):
'''
:param examples: [{word:[..], pos:[..], head:[..], label:[..]}..]，一个字典表示一个句子，里面用token2id的id表示
:return: [[([n_feature长的特征], [可以采取的所有操作], 真实的操作)..]..]
'''
all_instances = []
succ = 0
for id, ex in enumerate(logged_loop(examples)):
n_words = len(ex['word']) - 1
# arcs = {(h, t, label)}
stack = [0]
buf = [i + 1 for i in range(n_words)]
arcs = []
instances = []
for i in range(n_words * 2): # 每个词有进有出，一共有2n步
gold_t = self.get_oracle(stack, buf, ex)
if gold_t is None:
break
legal_labels = self.legal_labels(stack, buf)
assert legal_labels[gold_t] == 1
instances.append((self.extract_features(stack, buf, arcs, ex),
legal_labels, gold_t))
if gold_t == self.n_trans - 1:
stack.append(buf[0])
buf = buf[1:]
elif gold_t < self.n_deprel: # 说明是L-XXX
arcs.append((stack[-1], stack[-2], gold_t))
stack = stack[:-2] + [stack[-1]]
else:
arcs.append((stack[-2], stack[-1], gold_t - self.n_deprel))
stack = stack[:-1]
else:
succ += 1
all_instances += instances
return all_instances
