def __init__(self,
vocab: Vocabulary,
bert_model: Union[str, BertModel],
embedding_dropout: float = 0.0,
initializer: InitializerApplicator = InitializerApplicator(),
regularizer: Optional[RegularizerApplicator] = None,
label_smoothing: float = None,
ignore_span_metric: bool = False,
srl_eval_path: str = DEFAULT_SRL_EVAL_PATH) -> None:
super().__init__(vocab, regularizer)
if isinstance(bert_model, str):
self.bert_model = BertModel.from_pretrained(bert_model)
else:
self.bert_model = bert_model
self.num_classes = self.vocab.get_vocab_size("labels")
if srl_eval_path is not None:
# For the span based evaluation, we don't want to consider labels
# for verb, because the verb index is provided to the model.
self.span_metric = SrlEvalScorer(srl_eval_path,
ignore_classes=["V"])
else:
self.span_metric = None
self.tag_projection_layer = Linear(self.bert_model.config.hidden_size,
self.num_classes)
self.embedding_dropout = Dropout(p=embedding_dropout)
self._label_smoothing = label_smoothing
self.ignore_span_metric = ignore_span_metric
initializer(self)
def __init__(
self,
vocab: Vocabulary,
bert_model: Union[str, BertModel],
embedding_dropout: float = 0.0,
initializer: InitializerApplicator = InitializerApplicator(),
regularizer: Optional[RegularizerApplicator] = None,
label_smoothing: float = None,
ignore_span_metric: bool = False,
srl_eval_path: str = DEFAULT_SRL_EVAL_PATH,
parser_path:
str = "/home/rizwan/.allennlp/cache/elmo-allennlp_constituency_parser"
) -> None:
super().__init__(vocab, regularizer)
if isinstance(bert_model, str):
self.bert_model = BertModel.from_pretrained(bert_model)
else:
self.bert_model = bert_model
self.num_classes = self.vocab.get_vocab_size("labels")
if srl_eval_path is not None:
# For the span based evaluation, we don't want to consider labels
# for verb, because the verb index is provided to the model.
self.span_metric = SrlEvalScorer(srl_eval_path,
ignore_classes=["V"])
else:
self.span_metric = None
self.tag_projection_layer = Linear(
2 * self.bert_model.config.hidden_size, self.num_classes)
self.embedding_dropout = Dropout(p=embedding_dropout)
self._label_smoothing = label_smoothing
self.ignore_span_metric = ignore_span_metric
device = 0 if torch.cuda.is_available() else -1
self.parser = Predictor.from_path(parser_path, cuda_device=device)
self.syntax_roberta = RobertaModel.from_pretrained(
'../fairseq/checkpoints_768', 'checkpoint_best.pt')
self.syntax_roberta.eval()
self.matrix_attention = DotProductMatrixAttention()
initializer(self)
def __init__(
self,
vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
encoder: Seq2SeqEncoder,
binary_feature_dim: int,
embedding_dropout: float = 0.0,
initializer: InitializerApplicator = InitializerApplicator(),
label_smoothing: float = None,
ignore_span_metric: bool = False,
srl_eval_path: str = DEFAULT_SRL_EVAL_PATH,
**kwargs,
) -> None:
super().__init__(vocab, **kwargs)
self.text_field_embedder = text_field_embedder
self.num_classes = self.vocab.get_vocab_size("labels")
if srl_eval_path is not None:
# For the span based evaluation, we don't want to consider labels
# for verb, because the verb index is provided to the model.
self.span_metric = SrlEvalScorer(srl_eval_path, ignore_classes=["V"])
else:
self.span_metric = None
self.encoder = encoder
# There are exactly 2 binary features for the verb predicate embedding.
self.binary_feature_embedding = Embedding(
num_embeddings=2, embedding_dim=binary_feature_dim
)
self.tag_projection_layer = TimeDistributed(
Linear(self.encoder.get_output_dim(), self.num_classes)
)
self.embedding_dropout = Dropout(p=embedding_dropout)
self._label_smoothing = label_smoothing
self.ignore_span_metric = ignore_span_metric
check_dimensions_match(
text_field_embedder.get_output_dim() + binary_feature_dim,
encoder.get_input_dim(),
"text embedding dim + verb indicator embedding dim",
"encoder input dim",
)
initializer(self)
def __init__(self, vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
encoder: Seq2SeqEncoder,
binary_feature_dim: int,
embedding_dropout: float = 0.0,
initializer: InitializerApplicator = InitializerApplicator(),
regularizer: Optional[RegularizerApplicator] = None,
label_smoothing: float = None,
ignore_span_metric: bool = False,
srl_eval_path: str = DEFAULT_SRL_EVAL_PATH) -> None:
super(GCN_model, self).__init__(vocab, regularizer)
self.text_field_embedder = text_field_embedder
self.num_classes = self.vocab.get_vocab_size("labels")
if srl_eval_path is not None:
# For the span based evaluation, we don't want to consider labels
# for verb, because the verb index is provided to the model.
self.span_metric = SrlEvalScorer(srl_eval_path, ignore_classes=["V"])
else:
self.span_metric = None
self.encoder = encoder
self.gcn_layer = GCN(nfeat=self.encoder.get_output_dim(), nhid=200, nclass=64, dropout=0.1)
self.decoder = PytorchSeq2SeqWrapper(
StackedAlternatingLstm(input_size=64, hidden_size=32,
num_layers=2, recurrent_dropout_probability=0.1, use_highway=True))
self.tag_projection_layer = TimeDistributed(Linear(32, self.num_classes))
# self.tag_projection_layer = TimeDistributed(Linear(self.encoder.get_output_dim(), self.num_classes))
# There are exactly 2 binary features for the verb predicate embedding.
self.binary_feature_embedding = Embedding(2, binary_feature_dim)
self.embedding_dropout = Dropout(p=embedding_dropout)
self._label_smoothing = label_smoothing
self.ignore_span_metric = ignore_span_metric
check_dimensions_match(text_field_embedder.get_output_dim() + binary_feature_dim,
encoder.get_input_dim(),
"text embedding dim + verb indicator embedding dim",
"encoder input dim")
initializer(self)