def get_sentence_examples(self, questions, prefix):
data_list = []
for index, data in enumerate(questions):
data = data.strip().split('\t')
guid = '%s-%d' % (prefix, index)
text_a = tokenization.convert_to_unicode(str(data[0]))
text_b = tokenization.convert_to_unicode(str(data[1]))
label = str(data[2])
data_list.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
return data_list
def _to_example(sentences):
import re
"""
sentences to InputExample
:param sentences: list of strings
:return: list of InputExample
"""
unique_id = 0
for ss in sentences:
line = tokenization.convert_to_unicode(ss)
if not line:
continue
line = line.strip()
text_a = None
text_b = None
m = re.match(r"^(.*) \|\|\| (.*)$", line)
if m is None:
text_a = line
else:
text_a = m.group(1)
text_b = m.group(2)
yield InputExample(unique_id=unique_id,
text_a=text_a,
text_b=text_b)
unique_id += 1