def __call__(self,
texts_a: List[str],
texts_b: Optional[List[str]] = None) -> List[InputFeatures]:
"""Call Bert convert_examples_to_features function to tokenize and create masks.
texts_a and texts_b are separated by [SEP] token
Args:
texts_a: list of texts,
texts_b: list of texts, it could be None, e.g. single sentence classification task
Returns:
batch of InputFeatures with subtokens, subtoken ids, subtoken mask, segment mask.
"""
if texts_b is None:
texts_b = [None] * len(texts_a)
# unique_id is not used
examples = [
InputExample(unique_id=0, text_a=text_a, text_b=text_b)
for text_a, text_b in zip(texts_a, texts_b)
]
return convert_examples_to_features(examples, self.max_seq_length,
self.tokenizer)
def __call__(self, batch: List[List[str]]) -> List[List[InputFeatures]]:
"""Call BERT convert_examples_to_features function to tokenize and create masks.
Args:
batch: list of elemenents where the first element represents the batch with contexts
and the rest of elements represent response candidates batches
Returns:
list of feature batches with subtokens, subtoken ids, subtoken mask, segment mask
for the context and each of response candidates separately.
"""
if isinstance(batch[0], str):
batch = [batch]
samples = []
for i in range(len(batch[0])):
s = []
for el in batch:
s.append(el[i])
samples.append(s)
s_empt = [None] * len(samples[0])
# TODO: add unique id
examples = []
for s in samples:
ex = [InputExample(unique_id=0, text_a=text_a, text_b=text_b) for text_a, text_b in
zip(s, s_empt)]
examples.append(ex)
features = [convert_examples_to_features(el, self.max_seq_length, self.tokenizer) for el in examples]
return features
def __call__(self, batch: List[List[str]]) -> List[List[InputFeatures]]:
"""Call BERT convert_examples_to_features function to tokenize and create masks.
Args:
batch: list of elemenents where the first element represents the batch with contexts
and the rest of elements represent response candidates batches
Returns:
list of feature batches with subtokens, subtoken ids, subtoken mask, segment mask.
"""
if isinstance(batch[0], str):
batch = [batch]
cont_resp_pairs = []
if len(batch[0]) == 1:
contexts = batch[0]
responses_empt = [None] * len(batch)
cont_resp_pairs.append(zip(contexts, responses_empt))
else:
contexts = [el[0] for el in batch]
for i in range(1, len(batch[0])):
responses = []
for el in batch:
responses.append(el[i])
cont_resp_pairs.append(zip(contexts, responses))
examples = []
for s in cont_resp_pairs:
ex = [InputExample(unique_id=0, text_a=context, text_b=response) for context, response in s]
examples.append(ex)
features = [convert_examples_to_features(el, self.max_seq_length, self.tokenizer) for el in examples]
return features
def __call__(self, batch):
if isinstance(batch[0], str):
batch = [batch]
samples = []
for i in range(len(batch[0])):
s = []
for el in batch:
s.append(el[i])
samples.append(s)
s_dummy = [None] * len(samples[0])
# TODO: add unique id
examples = []
for s in samples:
ex = [
InputExample(unique_id=0, text_a=text_a, text_b=text_b)
for text_a, text_b in zip(s, s_dummy)
]
examples.append(ex)
features = [
convert_examples_to_features(el, self.max_seq_length,
self.tokenizer) for el in examples
]
return features
