Skip to content

crf_tagger

allennlp_models.tagging.models.crf_tagger

[SOURCE]


CrfTagger#

@Model.register("crf_tagger")
class CrfTagger(Model):
 | def __init__(
 |     self,
 |     vocab: Vocabulary,
 |     text_field_embedder: TextFieldEmbedder,
 |     encoder: Seq2SeqEncoder,
 |     label_namespace: str = "labels",
 |     feedforward: Optional[FeedForward] = None,
 |     label_encoding: Optional[str] = None,
 |     include_start_end_transitions: bool = True,
 |     constrain_crf_decoding: bool = None,
 |     calculate_span_f1: bool = None,
 |     dropout: Optional[float] = None,
 |     verbose_metrics: bool = False,
 |     initializer: InitializerApplicator = InitializerApplicator(),
 |     top_k: int = 1,
 |     ignore_loss_on_o_tags: bool = False,
 |     label_weights: Optional[Dict[str, float]] = None,
 |     weight_strategy: str = None,
 |     **kwargs
 | ) -> None

The CrfTagger encodes a sequence of text with a Seq2SeqEncoder, then uses a Conditional Random Field model to predict a tag for each token in the sequence.

Registered as a Model with name "crf_tagger".

Parameters

  • vocab : Vocabulary
    A Vocabulary, required in order to compute sizes for input/output projections.
  • text_field_embedder : TextFieldEmbedder
    Used to embed the tokens TextField we get as input to the model.
  • encoder : Seq2SeqEncoder
    The encoder that we will use in between embedding tokens and predicting output tags.
  • label_namespace : str, optional (default = labels)
    This is needed to compute the SpanBasedF1Measure metric. Unless you did something unusual, the default value should be what you want.
  • feedforward : FeedForward, optional (default = None)
    An optional feedforward layer to apply after the encoder.
  • label_encoding : str, optional (default = None)
    Label encoding to use when calculating span f1 and constraining the CRF at decoding time . Valid options are "BIO", "BIOUL", "IOB1", "BMES". Required if calculate_span_f1 or constrain_crf_decoding is true.
  • include_start_end_transitions : bool, optional (default = True)
    Whether to include start and end transition parameters in the CRF.
  • constrain_crf_decoding : bool, optional (default = None)
    If True, the CRF is constrained at decoding time to produce valid sequences of tags. If this is True, then label_encoding is required. If None and label_encoding is specified, this is set to True. If None and label_encoding is not specified, it defaults to False.
  • calculate_span_f1 : bool, optional (default = None)
    Calculate span-level F1 metrics during training. If this is True, then label_encoding is required. If None and label_encoding is specified, this is set to True. If None and label_encoding is not specified, it defaults to False.
  • dropout : float, optional (default = None)
    Dropout probability.
  • verbose_metrics : bool, optional (default = False)
    If true, metrics will be returned per label class in addition to the overall statistics.
  • initializer : InitializerApplicator, optional (default = InitializerApplicator())
    Used to initialize the model parameters.
  • top_k : int, optional (default = 1)
    If provided, the number of parses to return from the crf in output_dict['top_k_tags']. Top k parses are returned as a list of dicts, where each dictionary is of the form: {"tags": List, "score": float}. The "tags" value for the first dict in the list for each data_item will be the top choice, and will equal the corresponding item in output_dict['tags']
  • ignore_loss_on_o_tags : bool, optional (default = False)
    If True, we compute the loss only for actual spans in tags, and not on O tokens. This is useful for computing gradients of the loss on a single span, for interpretation / attacking.
  • label_weights : Dict[str, float], optional (default = None)
    A mapping {label : weight} to be used in the loss function in order to give different weights for each token depending on its label. This is useful to deal with highly unbalanced datasets. There are three available strategies to deal with weighted labels (see below). The default strategy is "emission".
  • weight_strategy : str, optional (default = None)
    If label_weights is given and this is None, then it is the same as "emission". It indicates which strategy is used to sample weighting. Valid options are: "emission", "emission_transition", "lannoy". If "emission" then the emission score of each tag is multiplied by the corresponding weight (as given by label_weights). If "emission_transition", both emission and transition scores of each tag are multiplied by the corresponding weight. In this case, a transition score t(i,j), between consecutive tokens i and j, is multiplied by w[tags[i]], i.e., the weight related to the tag of token i. If weight_strategy is "lannoy" then we use the strategy proposed by Lannoy et al. (2019). You can see an experimental comparison among these three strategies and a brief discussion of their differences here.

forward#

class CrfTagger(Model):
 | ...
 | def forward(
 |     self,
 |     tokens: TextFieldTensors,
 |     tags: torch.LongTensor = None,
 |     metadata: List[Dict[str, Any]] = None,
 |     ignore_loss_on_o_tags: Optional[bool] = None,
 |     **kwargs
 | ) -> Dict[str, torch.Tensor]

Parameters

  • tokens : TextFieldTensors
    The output of TextField.as_array(), which should typically be passed directly to a TextFieldEmbedder. This output is a dictionary mapping keys to TokenIndexer tensors. At its most basic, using a SingleIdTokenIndexer this is : {"tokens": Tensor(batch_size, num_tokens)}. This dictionary will have the same keys as were used for the TokenIndexers when you created the TextField representing your sequence. The dictionary is designed to be passed directly to a TextFieldEmbedder, which knows how to combine different word representations into a single vector per token in your input.
  • tags : torch.LongTensor, optional (default = None)
    A torch tensor representing the sequence of integer gold class labels of shape (batch_size, num_tokens).
  • metadata : List[Dict[str, Any]], optional (default = None)
    metadata containing the original words in the sentence to be tagged under a 'words' key.
  • ignore_loss_on_o_tags : Optional[bool], optional (default = None)
    If True, we compute the loss only for actual spans in tags, and not on O tokens. This is useful for computing gradients of the loss on a single span, for interpretation / attacking. If None, self.ignore_loss_on_o_tags is used instead.

Returns

  • An output dictionary consisting of:

  • logits : torch.FloatTensor
    The logits that are the output of the tag_projection_layer

  • mask : torch.BoolTensor
    The text field mask for the input tokens
  • tags : List[List[int]]
    The predicted tags using the Viterbi algorithm.
  • loss : torch.FloatTensor, optional
    A scalar loss to be optimised. Only computed if gold label tags are provided.

make_output_human_readable#

class CrfTagger(Model):
 | ...
 | def make_output_human_readable(
 |     self,
 |     output_dict: Dict[str, torch.Tensor]
 | ) -> Dict[str, torch.Tensor]

Converts the tag ids to the actual tags. output_dict["tags"] is a list of lists of tag_ids, so we use an ugly nested list comprehension.

get_metrics#

class CrfTagger(Model):
 | ...
 | def get_metrics(self, reset: bool = False) -> Dict[str, float]

default_predictor#

class CrfTagger(Model):
 | ...
 | default_predictor = "sentence_tagger"