allennlp.models.graph_parser

class allennlp.models.graph_parser.GraphParser(vocab: allennlp.data.vocabulary.Vocabulary, text_field_embedder: allennlp.modules.text_field_embedders.text_field_embedder.TextFieldEmbedder, encoder: allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder, tag_representation_dim: int, arc_representation_dim: int, tag_feedforward: allennlp.modules.feedforward.FeedForward = None, arc_feedforward: allennlp.modules.feedforward.FeedForward = None, pos_tag_embedding: allennlp.modules.token_embedders.embedding.Embedding = None, dropout: float = 0.0, input_dropout: float = 0.0, edge_prediction_threshold: float = 0.5, initializer: allennlp.nn.initializers.InitializerApplicator = <allennlp.nn.initializers.InitializerApplicator object>, regularizer: typing.Union[allennlp.nn.regularizers.regularizer_applicator.RegularizerApplicator, NoneType] = None) → None[source]

Bases: allennlp.models.model.Model

A Parser for arbitrary graph stuctures.

Parameters:
vocab : Vocabulary, required

A Vocabulary, required in order to compute sizes for input/output projections.

text_field_embedder : TextFieldEmbedder, required

Used to embed the tokens TextField we get as input to the model.

encoder : Seq2SeqEncoder

The encoder (with its own internal stacking) that we will use to generate representations of tokens.

tag_representation_dim : int, required.

The dimension of the MLPs used for arc tag prediction.

arc_representation_dim : int, required.

The dimension of the MLPs used for arc prediction.

tag_feedforward : FeedForward, optional, (default = None).

The feedforward network used to produce tag representations. By default, a 1 layer feedforward network with an elu activation is used.

arc_feedforward : FeedForward, optional, (default = None).

The feedforward network used to produce arc representations. By default, a 1 layer feedforward network with an elu activation is used.

pos_tag_embedding : Embedding, optional.

Used to embed the pos_tags SequenceLabelField we get as input to the model.

dropout : float, optional, (default = 0.0)

The variational dropout applied to the output of the encoder and MLP layers.

input_dropout : float, optional, (default = 0.0)

The dropout applied to the embedded text input.

edge_prediction_threshold : int, optional (default = 0.5)

The probability at which to consider a scored edge to be ‘present’ in the decoded graph. Must be between 0 and 1.

initializer : InitializerApplicator, optional (default=``InitializerApplicator()``)

Used to initialize the model parameters.

regularizer : RegularizerApplicator, optional (default=``None``)

If provided, will be used to calculate the regularization penalty during training.

decode(output_dict: typing.Dict[str, torch.Tensor]) → typing.Dict[str, torch.Tensor][source]

Takes the result of forward() and runs inference / decoding / whatever post-processing you need to do your model. The intent is that model.forward() should produce potentials or probabilities, and then model.decode() can take those results and run some kind of beam search or constrained inference or whatever is necessary. This does not handle all possible decoding use cases, but it at least handles simple kinds of decoding.

This method modifies the input dictionary, and also returns the same dictionary.

By default in the base class we do nothing. If your model has some special decoding step, override this method.

forward(tokens: typing.Dict[str, torch.LongTensor], pos_tags: torch.LongTensor = None, metadata: typing.List[typing.Dict[str, typing.Any]] = None, arc_tags: torch.LongTensor = None) → typing.Dict[str, torch.Tensor][source]
Parameters:
tokens : Dict[str, torch.LongTensor], required

The output of TextField.as_array().

pos_tags : torch.LongTensor, optional, (default = None).

The output of a SequenceLabelField containing POS tags.

arc_tags : torch.LongTensor, optional (default = None)

A torch tensor representing the sequence of integer indices denoting the parent of every word in the dependency parse. Has shape (batch_size, sequence_length, sequence_length).

Returns:
An output dictionary.
get_metrics(reset: bool = False) → typing.Dict[str, float][source]

Returns a dictionary of metrics. This method will be called by allennlp.training.Trainer in order to compute and use model metrics for early stopping and model serialization. We return an empty dictionary here rather than raising as it is not required to implement metrics for a new model. A boolean reset parameter is passed, as frequently a metric accumulator will have some state which should be reset between epochs. This is also compatible with Metrics should be populated during the call to ``forward`, with the Metric handling the accumulation of the metric until this method is called.