def encode(self, example: InputExample, tokenizer, seq_length, args):
if args.pretrained_bert:
ids_list, types_list, paddings_list = [], [], []
else:
ids_list, positions_list, sep_list = [], [], []
tokens_a = tokenizer.EncodeAsIds(example.text_a).tokenization
tokens_b = tokenizer.EncodeAsIds(example.text_b).tokenization if example.text_b else None
for answer in example.meta["candidates"]:
answer_ids = tokenizer.EncodeAsIds(answer).tokenization
total_length = len(tokens_a) + len(tokens_b) + len(answer_ids)
total_length += num_special_tokens_to_add(tokens_a, tokens_b + answer_ids, None, add_cls=True, add_sep=True,
add_piece=False)
if total_length > seq_length:
self.num_truncated += 1
data = build_input_from_ids(tokens_a, tokens_b + answer_ids, None, seq_length, tokenizer, args,
add_cls=True, add_sep=True, add_piece=False)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
if args.pretrained_bert:
ids_list.append(ids)
types_list.append(types)
paddings_list.append(paddings)
else:
ids_list.append(ids)
positions_list.append(position_ids)
sep_list.append(sep)
label = example.label
label = self.get_labels().index(label)
if args.pretrained_bert:
sample = build_sample(ids_list, label=label, types=types_list, paddings=paddings_list,
unique_id=example.guid)
else:
sample = build_sample(ids_list, positions=positions_list, masks=sep_list, label=label,
unique_id=example.guid)
return sample
def __getitem__(self, idx):
document_idx = bisect_right(self.weights, idx)
idx = idx - self.left_weights[document_idx]
start_idx = idx * self.overalapping_eval
end_idx = start_idx + self.max_seq_len
tokens = self.documents[document_idx][start_idx:end_idx]
if self.block_lm:
if idx == 0 or self.unidirectional:
prompt, text = tokens[:1], tokens[1:]
else:
prompt_length = self.max_seq_len - self.overalapping_eval
prompt, text = tokens[:prompt_length], tokens[prompt_length:]
prompt = prompt + [self.mask_id]
num_special_tokens = num_special_tokens_to_add(prompt, None, text, add_cls=True, add_sep=False,
add_piece=True,
add_eos=False)
data = build_input_from_ids(prompt, None, text, self.max_seq_len + num_special_tokens + 1, self.tokenizer,
args=self.args, add_cls=True, add_sep=False, add_piece=True, add_eos=False, mask_id=self.mask_id)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
if idx != 0 and self.unidirectional:
loss_masks = np.array(loss_masks, dtype=np.int64)
loss_masks[:-self.overalapping_eval] = 0
return {'text': np.array(ids, dtype=np.int64), 'target': np.array(target_ids, dtype=np.int64),
'attention_mask': np.array(sep, dtype=np.int64), 'loss_mask': np.array(loss_masks, dtype=np.int64),
"position_id": np.array(position_ids, dtype=np.int64)}
else:
loss_masks = [1] * len(tokens)
if len(tokens) < self.max_seq_len:
tokens = tokens + [0] * (self.max_seq_len - len(tokens))
loss_masks = loss_masks + [0] * (self.max_seq_len - len(loss_masks))
if idx != 0:
loss_masks = np.array(loss_masks, dtype=np.int64)
loss_masks[:-self.overalapping_eval] = 0
return {'text': np.array(tokens, dtype=np.int64), 'loss_mask': np.array(loss_masks, dtype=np.int64)}
def __getitem__(self, idx):
tokens, answer = self.tokens[idx], self.labels[idx]
if self.block_lm:
if self.unidirectional:
tokens, answer_tokens = tokens[:1], tokens[1:] + answer
else:
answer_tokens = answer
tokens = tokens + [self.mask_id]
num_special_tokens = num_special_tokens_to_add(tokens,
None,
answer_tokens,
add_cls=True,
add_sep=False,
add_piece=True)
left_shift = len(tokens) + len(
answer_tokens) + num_special_tokens - self.max_seq_length
if left_shift > 0:
tokens = tokens[left_shift:]
data = build_input_from_ids(tokens,
None,
answer_tokens,
self.max_seq_length,
self.tokenizer,
args=self.args,
add_cls=True,
add_sep=False,
add_piece=True)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
if self.unidirectional:
loss_masks = np.array(loss_masks, dtype=np.int64)
last_index = len(loss_masks)
while loss_masks[last_index - 1] == 0:
last_index -= 1
loss_masks[:last_index - len(answer)] = 0
return {
'text': np.array(ids, dtype=np.int64),
'target': np.array(target_ids, dtype=np.int64),
'attention_mask': np.array(sep, dtype=np.int64),
'loss_mask': np.array(loss_masks, dtype=np.int64),
"position_id": np.array(position_ids, dtype=np.int64)
}
else:
left_shift = len(tokens) - self.max_seq_length
if left_shift > 0:
tokens = tokens[left_shift:]
ids = tokens + answer
if len(ids) < self.max_seq_length:
ids = ids + [0] * (self.max_seq_length - len(ids))
loss_masks = [0] * len(tokens) + [1] * len(answer)
if len(loss_masks) < self.max_seq_length:
loss_masks = loss_masks + [0] * (self.max_seq_length -
len(loss_masks))
return {
'text': np.array(ids, dtype=np.int64),
'loss_mask': np.array(loss_masks, dtype=np.int64)
}
def encode(self, example: InputExample, tokenizer, args):
if args.pretrained_bert:
ids_list, types_list, paddings_list = [], [], []
else:
ids_list, positions_list, sep_list = [], [], []
question = example.meta['question']
joiner = 'because' if question == 'cause' else 'so'
text_a = example.text_a + " " + joiner
tokens_a = tokenizer.EncodeAsIds(text_a).tokenization
for choice in [example.meta["choice1"], example.meta["choice2"]]:
tokens_b = tokenizer.EncodeAsIds(choice).tokenization
num_special_tokens = num_special_tokens_to_add(tokens_a,
tokens_b,
None,
add_cls=True,
add_sep=True,
add_piece=False)
if len(tokens_a) + len(
tokens_b) + num_special_tokens > args.seq_length:
self.num_truncated += 1
data = build_input_from_ids(tokens_a,
tokens_b,
None,
args.seq_length,
tokenizer,
args,
add_cls=True,
add_sep=True,
add_piece=False)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
if args.pretrained_bert:
ids_list.append(ids)
types_list.append(types)
paddings_list.append(paddings)
else:
ids_list.append(ids)
positions_list.append(position_ids)
sep_list.append(sep)
label = 0
if example.label is not None:
label = example.label
label = self.get_labels().index(label)
if args.pretrained_bert:
sample = build_sample(ids_list,
label=label,
types=types_list,
paddings=paddings_list,
unique_id=example.guid)
else:
sample = build_sample(ids_list,
positions=positions_list,
masks=sep_list,
label=label,
unique_id=example.guid)
return sample
def encode(self, example: InputExample, tokenizer, args):
text_a, text_b = self.get_classifier_input(example, tokenizer)
tokens_a = tokenizer.EncodeAsIds(text_a).tokenization
tokens_b = tokenizer.EncodeAsIds(text_b).tokenization
num_special_tokens = num_special_tokens_to_add(tokens_a,
tokens_b,
None,
add_cls=True,
add_sep=True,
add_piece=False)
if len(tokens_a) + len(
tokens_b) + num_special_tokens > args.seq_length:
self.num_truncated += 1
data = build_input_from_ids(tokens_a,
tokens_b,
None,
args.seq_length,
tokenizer,
args=args,
add_cls=True,
add_sep=True,
add_piece=False)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
label = 0
if example.label is not None:
label = example.label
label = self.get_labels().index(label)
if args.pretrained_bert:
sample = build_sample(ids,
label=label,
types=types,
paddings=paddings,
unique_id=example.guid)
else:
sample = build_sample(ids,
positions=position_ids,
masks=sep,
label=label,
unique_id=example.guid)
return sample
def encode(self,
example: InputExample,
priming: bool = False,
labeled: bool = False):
"""
Encode an input example using this pattern-verbalizer pair.
:param example: the input example to encode
:param priming: whether to use this example for priming
:param labeled: if ``priming=True``, whether the label should be appended to this example
:return: A tuple, consisting of a list of input ids and a list of token type ids
"""
if self.args.wsc_negative:
sample = super().encode(example, priming=priming, labeled=labeled)
return sample
if not priming:
assert not labeled, "'labeled' can only be set to true if 'priming' is also set to true"
tokenizer = self.tokenizer
prompt_id = tokenizer.num_tokens
raw_parts_a, raw_parts_b = self.get_parts(example)
raw_parts_a = [
x if isinstance(x, tuple) else (x, False) for x in raw_parts_a
]
def encode_input(raw_parts):
parts, flags = [], []
for x, s in raw_parts:
if isinstance(x, str):
x = tokenizer.EncodeAsIds(x)
flag = [0] * len(x)
elif isinstance(x, int):
flag = [1] * x
x = [prompt_id] * x
else:
flag = [0] * len(x)
parts.append((x, s))
flags.append((flag, x))
return parts, flags
parts_a, flags_a = encode_input(raw_parts_a)
parts_b, flags_b = None, None
if raw_parts_b:
raw_parts_b = [
x if isinstance(x, tuple) else (x, False) for x in raw_parts_b
]
parts_b, flags_b = encode_input(raw_parts_b)
answer = self.get_answers(example)[0]
answer_ids = get_verbalization_ids(answer,
tokenizer,
force_single_token=False)
answer_ids = answer_ids + [tokenizer.get_command('eop').Id]
self.num_truncated += self.truncate(parts_a,
parts_b,
answer_ids,
max_length=self.max_seq_length)
tokens_a = [token_id for part, _ in parts_a for token_id in part]
tokens_b = [token_id for part, _ in parts_b
for token_id in part] if parts_b else None
data = build_input_from_ids(tokens_a,
tokens_b,
answer_ids,
self.max_seq_length,
self.tokenizer,
args=self.args,
add_cls=True,
add_sep=False,
add_piece=True)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
prompt_pos = [
idx for idx, token in enumerate(ids) if token == prompt_id
]
ids = [token if token != prompt_id else 0 for token in ids]
if example.label is not None:
label = self.label_list.index(example.label)
else:
label = 0
return {
'text': np.array(ids, dtype=np.int64),
'target': np.array(target_ids, dtype=np.int64),
'attention_mask': np.array(sep, dtype=np.int64),
'loss_mask': np.array(loss_masks, dtype=np.int64),
"position_id": np.array(position_ids, dtype=np.int64),
'prompt_pos': np.array(prompt_pos, dtype=np.int64),
'label': label,
'uid': example.guid
}
def encode(self,
example: InputExample,
priming: bool = False,
labeled: bool = False):
"""
Encode an input example using this pattern-verbalizer pair.
:param example: the input example to encode
:param priming: whether to use this example for priming
:param labeled: if ``priming=True``, whether the label should be appended to this example
:return: A tuple, consisting of a list of input ids and a list of token type ids
"""
if not priming:
assert not labeled, "'labeled' can only be set to true if 'priming' is also set to true"
tokenizer = self.tokenizer
raw_parts_a, raw_parts_b = self.get_parts(example)
raw_parts_a = [
x if isinstance(x, tuple) else (x, False) for x in raw_parts_a
]
prompt_id = tokenizer.num_tokens
def encode_input(raw_parts):
parts, flags = [], []
for x, s in raw_parts:
if isinstance(x, str):
x = tokenizer.EncodeAsIds(x)
flag = [0] * len(x)
elif isinstance(x, int):
flag = [1] * x
x = [prompt_id] * x
else:
flag = [0] * len(x)
parts.append((x, s))
flags.append((flag, x))
return parts, flags
parts_a, flags_a = encode_input(raw_parts_a)
parts_b, flags_b = None, None
if raw_parts_b:
raw_parts_b = [
x if isinstance(x, tuple) else (x, False) for x in raw_parts_b
]
parts_b, flags_b = encode_input(raw_parts_b)
if self.is_multi_token:
answers = self.get_answers(example)
if not self.fast_decode:
ids_list, positions_list, sep_list, mask_list, target_list, prompt_list = [], [], [], [], [], []
for idx, answer in enumerate(answers):
this_parts_a, this_parts_b = copy.deepcopy(
parts_a), copy.deepcopy(parts_b)
answer_ids = get_verbalization_ids(
answer, tokenizer, force_single_token=False)
answer_ids = answer_ids + [tokenizer.get_command('eop').Id]
self.num_truncated += self.truncate(
this_parts_a,
this_parts_b,
answer_ids,
max_length=self.max_seq_length)
tokens_a = [
token_id for part, _ in this_parts_a
for token_id in part
]
tokens_b = [
token_id for part, _ in this_parts_b
for token_id in part
] if parts_b else None
data = build_input_from_ids(tokens_a,
tokens_b,
answer_ids,
self.max_seq_length,
self.tokenizer,
args=self.args,
add_cls=True,
add_sep=False,
add_piece=True,
mask_id=self.mask_id)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
prompt_pos = [
idx for idx, token in enumerate(ids)
if token == prompt_id
]
ids = [idx if idx != prompt_id else 0 for idx in ids]
prompt_list.append(prompt_pos)
ids_list.append(ids)
positions_list.append(position_ids)
sep_list.append(sep)
target_list.append(target_ids)
mask_list.append(loss_masks)
if example.label is not None:
label = self.label_list.index(example.label)
else:
label = 0
sample = build_sample(ids_list,
positions=positions_list,
masks=sep_list,
label=label,
logit_mask=mask_list,
target=target_list,
unique_id=example.guid,
prompt_ids=prompt_list)
return sample
else:
this_parts_a, this_parts_b = copy.deepcopy(
parts_a), copy.deepcopy(parts_b)
self.num_truncated += self.truncate(
this_parts_a,
this_parts_b,
None,
max_length=self.max_seq_length)
tokens_a = [
token_id for part, _ in this_parts_a for token_id in part
]
tokens_b = [
token_id for part, _ in this_parts_b for token_id in part
] if parts_b else None
data = build_input_from_ids(tokens_a,
tokens_b,
None,
self.max_seq_length,
self.tokenizer,
args=self.args,
add_cls=True,
add_sep=False,
add_piece=False)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
if example.label is not None:
label = self.label_list.index(example.label)
else:
label = 0
sample = build_sample(ids,
positions=position_ids,
masks=sep,
label=label,
unique_id=example.guid)
ids_list, positions_list, mask_list, target_list, logit_mask_list = [], [], [], [], []
for answer in answers:
answer_ids = get_verbalization_ids(
answer, tokenizer, force_single_token=False)
answer_ids = answer_ids + [tokenizer.get_command('eop').Id]
answer_ids = answer_ids[:self.max_dec_seq_length]
data = build_decoder_input(ids, answer_ids,
self.max_seq_length,
self.max_dec_seq_length,
tokenizer)
dec_ids, _, _, dec_position_ids, _, dec_target_ids, dec_loss_masks = data
ids_list.append(dec_ids)
positions_list.append(dec_position_ids)
mask_list.append(sep)
target_list.append(dec_target_ids)
logit_mask_list.append(dec_loss_masks)
sample = build_decoder_sample(sample, ids_list, positions_list,
mask_list, target_list,
logit_mask_list)
return sample
else:
self.num_truncated += self.truncate(parts_a,
parts_b, [],
max_length=self.max_seq_length)
tokens_a = [token_id for part, _ in parts_a for token_id in part]
tokens_b = [token_id for part, _ in parts_b
for token_id in part] if parts_b else None
if priming:
input_ids = tokens_a
if tokens_b:
input_ids += tokens_b
if labeled:
mask_idx = input_ids.index(self.mask_id)
assert mask_idx == 1, 'sequence of input_ids must contain a mask token'
assert len(
self.verbalize(example.label)
) == 1, 'priming only supports one verbalization per label'
verbalizer = self.verbalize(example.label)[0]
verbalizer_id = get_verbalization_ids(
verbalizer, self.tokenizer, force_single_token=True)
input_ids[mask_idx] = verbalizer_id
return input_ids
data = build_input_from_ids(tokens_a,
tokens_b,
None,
self.max_seq_length,
self.tokenizer,
args=self.args,
add_cls=True,
add_sep=False,
add_piece=True)
ids, types, paddings, position_ids, sep, target_ids, loss_masks = data
prompt_pos = [
idx for idx, token in enumerate(ids) if token == prompt_id
]
ids = [token if token != prompt_id else 0 for token in ids]
target_ids = self.get_verbalizer_ids()
if example.label is not None:
label = self.label_list.index(example.label)
else:
label = 0
sample = build_sample(ids=ids,
positions=position_ids,
target=target_ids,
masks=sep,
logit_mask=loss_masks,
label=label,
unique_id=example.guid,
prompt_ids=prompt_pos)
return sample