def parse_sentence(line):
str_len = len(line)
chars = []
for idx in range(str_len):
chars.append(line[idx])
bichars = []
for idx in range(str_len):
if idx == 0:
bichar = '-NULL-' + chars[idx]
else:
bichar = chars[idx - 1] + chars[idx]
bichars.append(bichar)
inst = Instance()
inst.chars = chars
inst.bichars = bichars
return inst
def parse_conll(info):
chars = []
gold_labels = []
for line in info:
id, c, l = line.split("\t")
chars.append(c)
gold_labels.append(l)
bichars = []
char_len = len(chars)
for idx in range(char_len):
if idx == 0:
bichar = '-NULL-' + chars[idx]
else:
bichar = chars[idx - 1] + chars[idx]
bichars.append(bichar)
inst = Instance()
inst.chars = chars
inst.gold_labels = gold_labels
return inst
def parse_sent(info):
words = info.split(' ')
chars = []
bichars = []
inst = Instance()
for w in words:
for c in w:
chars.append(c)
char_len = len(chars)
for idx in range(char_len):
if idx == 0:
bichar = '-NULL-' + chars[idx]
else:
bichar = chars[idx - 1] + chars[idx]
bichars.append(bichar)
#bichars.append(chars[char_len - 1] + '</s>')
inst.words = words
inst.chars = chars
inst.bichars = bichars
return inst