def _create_examples(self, lines, set_type):
examples = []
for (i, line) in enumerate(lines):
# skip headers
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
if set_type == 'test':
text_a = tokenization.convert_to_unicode(line[2])
# the test set we pass to this processor will also be labeled
label = tokenization.convert_to_unicode(line[1])
else:
text_a = tokenization.convert_to_unicode(line[2])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
# the training set is sorted such that all the '1's (labels) are arranged one after another followed
# by all the '0's.
# since the buffer size for the shuffle step is only 100 and batch size is relatively small e.g. 32, the model
# ends up being fed with all '1' examples followed by all '0' examples.
# shuffling at this stage ensures that each batch has a mix of '1's and '0's.
if set_type == 'train':
random.shuffle(examples)
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "%s-%s" % (set_type, i)
text_a = tokenization.convert_to_unicode(line[3])
text_b = tokenization.convert_to_unicode(line[4])
if set_type == "test":
label = "0"
else:
label = tokenization.convert_to_unicode(line[0])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=text_b,
label=label))
return examples
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
# Only the test set has a header
if set_type == "test" and i == 0:
continue
guid = "%s-%s" % (set_type, i)
if set_type == "test":
text_a = tokenization.convert_to_unicode(line[1])
label = "0"
else:
text_a = tokenization.convert_to_unicode(line[3])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
return examples
def get_dev_examples(self, data_dir):
"""See base class."""
lines = self._read_tsv(os.path.join(data_dir, "xnli.dev.tsv"))
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "dev-%d" % (i)
language = tokenization.convert_to_unicode(line[0])
if language != tokenization.convert_to_unicode(self.language):
continue
text_a = tokenization.convert_to_unicode(line[6])
text_b = tokenization.convert_to_unicode(line[7])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=text_b,
label=label))
return examples
def get_train_examples(self, data_dir):
"""See base class."""
lines = self._read_tsv(
os.path.join(data_dir, "multinli",
"multinli.train.%s.tsv" % self.language))
examples = []
for (i, line) in enumerate(lines):
if i == 0:
continue
guid = "train-%d" % (i)
text_a = tokenization.convert_to_unicode(line[0])
text_b = tokenization.convert_to_unicode(line[1])
label = tokenization.convert_to_unicode(line[2])
if label == tokenization.convert_to_unicode("contradictory"):
label = tokenization.convert_to_unicode("contradiction")
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=text_b,
label=label))
return examples
def _create_examples(self, lines, set_type):
examples = []
for (i, line) in enumerate(lines):
# skip headers
if i == 0:
continue
guid = "%s-%s" % (set_type, line[0])
if set_type == 'test':
text_a = tokenization.convert_to_unicode(line[3])
# for the CFE dataset, we have a legit label even for the test set
label = tokenization.convert_to_unicode(line[1])
else:
text_a = tokenization.convert_to_unicode(line[3])
label = tokenization.convert_to_unicode(line[1])
examples.append(
InputExample(guid=guid,
text_a=text_a,
text_b=None,
label=label))
return examples
def create_training_instances(input_files, tokenizer, max_seq_length,
dupe_factor, short_seq_prob, masked_lm_prob,
max_predictions_per_seq, rng):
"""Create `TrainingInstance`s from raw text."""
all_documents = [[]]
# Input file format:
# (1) One sentence per line. These should ideally be actual sentences, not
# entire paragraphs or arbitrary spans of text. (Because we use the
# sentence boundaries for the "next sentence prediction" task).
# (2) Blank lines between documents. Document boundaries are needed so
# that the "next sentence prediction" task doesn't span between documents.
for input_file in input_files:
with tf.gfile.GFile(input_file, "r") as reader:
while True:
line = tokenization.convert_to_unicode(reader.readline())
if not line:
break
line = line.strip()
# Empty lines are used as document delimiters
if not line:
all_documents.append([])
tokens = tokenizer.tokenize(line)
if tokens:
all_documents[-1].append(tokens)
# Remove empty documents
all_documents = [x for x in all_documents if x]
rng.shuffle(all_documents)
vocab_words = list(tokenizer.vocab.keys())
instances = []
for _ in range(dupe_factor):
for document_index in range(len(all_documents)):
instances.extend(
create_instances_from_document(all_documents, document_index,
max_seq_length, short_seq_prob,
masked_lm_prob,
max_predictions_per_seq,
vocab_words, rng))
rng.shuffle(instances)
return instances
def read_examples(input_file):
"""Read a list of `InputExample`s from an input file."""
examples = []
unique_id = 0
with tf.gfile.GFile(input_file, "r") as reader:
while True:
line = tokenization.convert_to_unicode(reader.readline())
if not line:
break
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)
examples.append(
InputExample(unique_id=unique_id, text_a=text_a,
text_b=text_b))
unique_id += 1
return examples
