def output_ports(self):
"""Returns definitions of module output ports.
input_ids:
indices of tokens which constitute batches of text segments
input_type_ids:
tensor with 0's and 1's to denote the text segment type
input_mask:
bool tensor with 0s in place of tokens to be masked
loss_mask:
used to mask and ignore tokens in the loss function
subtokens_mask:
used to ignore the outputs of unwanted tokens in
the inference and evaluation like the start and end tokens
intents:
intents labels
slots:
slots labels
"""
return {
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_type_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"loss_mask": NeuralType(('B', 'T'), MaskType()),
"subtokens_mask": NeuralType(('B', 'T'), ChannelType()),
"intents": NeuralType(tuple('B'), LabelsType()),
"slots": NeuralType(('B', 'T'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
input_ids: indices of tokens which constitute batches of text segments
0: AxisType(BatchTag)
1: AxisType(TimeTag)
input_mask: bool tensor with 0s in place of tokens to be masked
0: AxisType(BatchTag)
1: AxisType(TimeTag)
labels: indices of tokens which should be predicted from each of the
corresponding tokens in input_ids; for left-to-right language
modeling equals to input_ids shifted by 1 to the right
0: AxisType(BatchTag)
1: AxisType(TimeTag)
"""
return {
# "input_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "input_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "labels": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"labels": NeuralType(('B', 'T'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
src_ids: indices of tokens which correspond to source sentences
src_mask: bool tensor with 0s in place of source tokens to be masked
tgt_ids: indices of tokens which correspond to target sentences
tgt_mask: bool tensor with 0s in place of target tokens to be masked
labels: indices of tokens which should be predicted from each of the
corresponding target tokens in tgt_ids; for standard neural
machine translation equals to tgt_ids shifted by 1 to the right
sent_ids: indices of the sentences in a batch; important for
evaluation with external metrics, such as SacreBLEU
"""
return {
# "src_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "src_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "tgt_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "tgt_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "labels": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "sent_ids": NeuralType({0: AxisType(BatchTag)}),
"src_ids": NeuralType(('B', 'T'), ChannelType()),
"src_mask": NeuralType(('B', 'T'), ChannelType()),
"tgt_ids": NeuralType(('B', 'T'), ChannelType()),
"tgt_mask": NeuralType(('B', 'T'), ChannelType()),
"labels": NeuralType(('B', 'T'), LabelsType()),
"sent_ids": NeuralType(tuple('B'), ChannelType()),
}
def input_ports(self):
"""Returns definitions of module input ports.
"""
return {
"logits": NeuralType(('B', 'T', 'D'), LogitsType()),
"labels": NeuralType(('B', 'T'), LabelsType()),
"output_mask": NeuralType(('B', 'T'), MaskType(), optional=True),
}
def input_ports(self):
"""Returns definitions of module input ports.
"""
return {
# "logits": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag), 2: AxisType(ChannelTag)}),
# "target_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
"logits": NeuralType(('B', 'T', 'D'), LogitsType()),
"target_ids": NeuralType(('B', 'T'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
"""
return {
# "input_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "input_type_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "input_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "loss_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "subtokens_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "punct_labels": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "capit_labels": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_type_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"loss_mask": NeuralType(('B', 'T'), ChannelType()),
"subtokens_mask": NeuralType(('B', 'T'), ChannelType()),
"punct_labels": NeuralType(('B', 'T'), LabelsType()),
"capit_labels": NeuralType(('B', 'T'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
input_ids:
indices of tokens which constitute batches of masked text segments
input_type_ids:
tensor with 0's and 1's to denote the text segment type
input_mask:
bool tensor with 0s in place of tokens to be masked
output_ids: indices of tokens which constitute batches of unmasked text segments
output_mask: bool tensor with 0s in place of tokens to be masked
labels: 0 or 1 for next sentence prediction classification
"""
return {
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_type_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"output_ids": NeuralType(('B', 'T'), LabelsType()),
"output_mask": NeuralType(('B', 'T'), MaskType()),
"labels": NeuralType(tuple('B'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
"""
return {
# "input_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "input_type_ids": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "input_mask": NeuralType({0: AxisType(BatchTag), 1: AxisType(TimeTag)}),
# "labels": NeuralType({0: AxisType(BatchTag)}),
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_type_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"labels": NeuralType(tuple('B'), LabelsType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
input_ids: indices of tokens which constitute batches of masked text segments
input_mask: bool tensor with 0s in place of source tokens to be masked
segment_ids: bool tensor with 0's and 1's to denote the text segment type
tgt_ids: indices of target tokens which constitute batches of masked text segments
labels_mask: bool tensor with 0s in place of label tokens to be masked
labels: indices of tokens which should be predicted from each of the
corresponding target tokens in tgt_ids
loss_mask: bool tensor with 0s in place of label tokens to be masked used for
CrossEntropyLossNM
"""
return {
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"segment_ids": NeuralType(('B', 'T'), ChannelType()),
"tgt_ids": NeuralType(('B', 'T'), LabelsType()),
"labels_mask": NeuralType(('B', 'T'), MaskType()),
"labels": NeuralType(('B', 'T'), LabelsType()),
"loss_mask": NeuralType(('B', 'T'), MaskType()),
}
def output_ports(self):
"""Returns definitions of module output ports.
input_ids:
indices of tokens which constitute batches of masked text segments
input_type_ids:
tensor with 0's and 1's to denote the text segment type
input_mask:
bool tensor with 0s in place of tokens to be masked
loss_mask:
used to mask and ignore tokens in the loss function: indices of tokens which constitute batches of unmasked text segments
subtokens_mask:
used to mask all but the first subtoken of the work, could be useful during inference
punct_labels: punctuation label ids
capit_labels: capit_labels label ids
"""
return {
"input_ids": NeuralType(('B', 'T'), ChannelType()),
"input_type_ids": NeuralType(('B', 'T'), ChannelType()),
"input_mask": NeuralType(('B', 'T'), ChannelType()),
"loss_mask": NeuralType(('B', 'T'), MaskType()),
"subtokens_mask": NeuralType(('B', 'T'), ChannelType()),
"punct_labels": NeuralType(('B', 'T'), LabelsType()),
"capit_labels": NeuralType(('B', 'T'), LabelsType()),
}
def input_ports(self):
"""Returns definitions of module input ports.
logit_intent_status (float): Output of SGD model
intent_status_labels (int): Intent labels
logit_req_slot_status (float): Output of SGD model
requested_slot_status (float): Takes value 1 if the corresponding slot is requested, 0 otherwise
req_slot_mask (bool): Masks requested slots not used for the particular service
logit_cat_slot_status (float): Output of SGD model
categorical_slot_status (int): The status of each categorical slot in the service
cat_slot_status_mask (bool): Masks categorical slots not used for the particular service
logit_cat_slot_value (float): Output of SGD model
categorical_slot_values (int): The index of the correct value for each categorical slot
logit_noncat_slot_status (float): Output of SGD model
noncategorical_slot_status (int): The status of each noncategorical slot in the service
noncat_slot_status_mask (bool): masks noncategorical slots not used for the particular service
logit_noncat_slot_start (float): Output of SGD model
logit_noncat_slot_end (float): Output of SGD model
noncategorical_slot_value_start (int): The index of the starting subword corresponding to the slot span for a non-categorical slot value
noncategorical_slot_value_end (int): The index of the ending (inclusive) subword corresponding to the slot span for a non-categorical slot value
"""
return {
"logit_intent_status": NeuralType(('B', 'T', 'C'), LogitsType()),
"intent_status_labels": NeuralType(('B'), LabelsType()),
"logit_req_slot_status": NeuralType(('B', 'T'), LogitsType()),
"requested_slot_status": NeuralType(('B', 'T'), LabelsType()),
"req_slot_mask": NeuralType(('B', 'T'), ChannelType()),
"logit_cat_slot_status": NeuralType(('B', 'T', 'C'), LogitsType()),
"categorical_slot_status": NeuralType(('B', 'T'), LabelsType()),
"cat_slot_status_mask": NeuralType(('B', 'T'), ChannelType()),
"logit_cat_slot_value": NeuralType(('B', 'T', 'C'), LogitsType()),
"categorical_slot_values": NeuralType(('B', 'T'), LabelsType()),
"logit_noncat_slot_status": NeuralType(('B', 'T', 'C'),
LogitsType()),
"noncategorical_slot_status": NeuralType(('B', 'T'), LabelsType()),
"noncat_slot_status_mask": NeuralType(('B', 'T'), ChannelType()),
"logit_noncat_slot_start": NeuralType(('B', 'T', 'C'),
LogitsType()),
"logit_noncat_slot_end": NeuralType(('B', 'T', 'C'), LogitsType()),
"noncategorical_slot_value_start": NeuralType(('B', 'T'),
LabelsType()),
"noncategorical_slot_value_end": NeuralType(('B', 'T'),
LabelsType()),
}