class Config(BasePairwiseClassificationModel.Config):
"""
Attributes:
encode_relations (bool): if `false`, return the concatenation of the two
representations; if `true`, also concatenate their pairwise absolute
difference and pairwise elementwise product (à la arXiv:1705.02364).
Default: `true`.
tied_representation: whether to use the same representation, with
tied weights, for all the input subrepresentations. Default: `true`.
"""
class ModelInput(BasePairwiseClassificationModel.Config.ModelInput):
tokens1: TokenTensorizer.Config = TokenTensorizer.Config(
column="text1")
tokens2: TokenTensorizer.Config = TokenTensorizer.Config(
column="text2")
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
raw_text: JoinStringTensorizer.Config = JoinStringTensorizer.Config(
columns=["text1", "text2"])
inputs: ModelInput = ModelInput()
embedding: WordEmbedding.Config = WordEmbedding.Config()
representation: Union[
BiLSTMDocAttention.Config,
DocNNRepresentation.Config] = BiLSTMDocAttention.Config()
shared_representations: bool = True
decoder: MLPDecoder.Config = MLPDecoder.Config()
# TODO: will need to support different output layer for contrastive loss
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
encode_relations: bool = True
class Config(ConfigBase):
representation: Union[
PureDocAttention.Config, BiLSTMDocAttention.Config,
DocNNRepresentation.Config, ] = BiLSTMDocAttention.Config()
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(ConfigBase):
representation: PairRepresentation.Config = PairRepresentation.Config()
decoder: MLPDecoder.Config = MLPDecoder.Config()
# TODO: will need to support different output layer for contrastive loss
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config()
)
class Config(Model.Config):
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config()
labels: LabelTensorizer.Config = LabelTensorizer.Config()
inputs: ModelInput = ModelInput()
embedding: WordEmbedding.Config = WordEmbedding.Config()
representation: Union[
PureDocAttention.Config, BiLSTMDocAttention.Config,
DocNNRepresentation.Config, ] = BiLSTMDocAttention.Config()
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(BaseModel.Config):
class InputConfig(ConfigBase):
tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
right_dense: FloatListTensorizer.Config = None
left_dense: FloatListTensorizer.Config = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
inputs: InputConfig = InputConfig()
encoder: RoBERTaEncoderBase.Config = RoBERTaEncoder.Config()
decoder: MLPDecoderTwoTower.Config = MLPDecoderTwoTower.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(BaseModel.Config):
class EncoderModelInput(BaseModel.Config.ModelInput):
tokens: Tensorizer.Config = Tensorizer.Config()
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2])
inputs: EncoderModelInput = EncoderModelInput()
encoder: RepresentationBase.Config
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(BaseModel.Config):
class BertModelInput(BaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(
max_seq_len=128)
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2])
inputs: BertModelInput = BertModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config())
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(BaseModel.Config):
class InputConfig(ConfigBase):
right_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
left_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
right_dense: Optional[FloatListTensorizer.Config] = None
left_dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
inputs: InputConfig = InputConfig()
right_encoder: RoBERTaEncoderBase.Config = RoBERTaEncoder.Config()
left_encoder: RoBERTaEncoderBase.Config = RoBERTaEncoder.Config()
decoder: MLPDecoderTwoTower.Config = MLPDecoderTwoTower.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
use_shared_encoder: Optional[bool] = False
class Config(BaseModel.Config):
class InputConfig(ConfigBase):
right_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
left_tokens: RoBERTaTensorizer.Config = RoBERTaTensorizer.Config()
right_dense: Optional[FloatListTensorizer.Config] = None
left_dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
inputs: InputConfig = InputConfig()
right_encoder: RoBERTaEncoderBase.Config = RoBERTaEncoder.Config()
left_encoder: RoBERTaEncoderBase.Config = RoBERTaEncoder.Config()
decoder: MLPDecoderTwoTower.Config = MLPDecoderTwoTower.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
use_shared_encoder: Optional[bool] = False
use_shared_embedding: Optional[bool] = False
vocab_size: Optional[int] = 250002
hidden_dim: Optional[int] = 768
padding_idx: Optional[int] = 1
class Config(ConfigBase):
representation: SeqRepresentation.Config = SeqRepresentation.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
decoder: MLPDecoder.Config = MLPDecoder.Config()
class Config(BaseModel.Config):
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config()
)
encode_relations: bool = True
class Config(BaseModel.Config):
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: Union[
ClassificationOutputLayer.Config, PairwiseCosineDistanceOutputLayer.Config
] = ClassificationOutputLayer.Config()
encode_relations: bool = True