def regular_encode(texts: list,
tokenizer: transformers.AutoTokenizer,
maxlen: int = 512,
multi_class: bool = True):
"""
Encode sentences for input to Transformer models.
:param texts: list of strings to be encoded
:param tokenizer: tokenizer for encoding
:param maxlen: max number of characters of input string being encoded
:param multi_class: if True, the default truncation is applied. If False, implies auxillary input and
custom truncation is applied.
:return: numpy array of encoded strings
"""
# TODO: Intersphinx link to transformers.AutoTokenizer is failing. What's wrong with my docs/source/conf.py?
if not multi_class:
# If len > maxlen, truncate text upto maxlen-8 characters and append the 8-character auxillary input
texts = [
text[:maxlen - 8] + text[-8:] if len(text) > maxlen else text
for text in texts
]
enc_di = tokenizer.batch_encode_plus(
texts,
return_attention_mask=False,
return_token_type_ids=False,
pad_to_max_length=True,
# sep_token='[SEP]',
max_length=maxlen,
truncation=True) # Is this what we want?
return np.array(enc_di['input_ids'])
def regular_encode(texts: list, tokenizer: transformers.AutoTokenizer, maxlen: int = 512):
"""
Encode sentences for input to Transformer models.
:param texts: list of strings to be encoded
:param tokenizer: tokenizer for encoding
:param maxlen: max number of characters of input string being encoded
:return: numpy array of encoded strings
"""
# TODO: Intersphinx link to transformers.AutoTokenizer is failing. What's wrong with my docs/source/conf.py?
enc_di = tokenizer.batch_encode_plus(texts,
return_attention_mask=False,
return_token_type_ids=False,
pad_to_max_length=True,
# sep_token='[SEP]',
max_length=maxlen,
truncation=True) # Is this what we want?
return np.array(enc_di['input_ids'])
