Skip to content




class AttachmentScores(Metric):
 | def __init__(self, ignore_classes: List[int] = None) -> None

Computes labeled and unlabeled attachment scores for a dependency parse, as well as sentence level exact match for both labeled and unlabeled trees. Note that the input to this metric is the sampled predictions, not the distribution itself.


  • ignore_classes : List[int], optional (default = None)
    A list of label ids to ignore when computing metrics.


class AttachmentScores(Metric):
 | ...
 | def __call__(
 |     self,
 |     predicted_indices: torch.Tensor,
 |     predicted_labels: torch.Tensor,
 |     gold_indices: torch.Tensor,
 |     gold_labels: torch.Tensor,
 |     mask: Optional[torch.BoolTensor] = None
 | )


  • predicted_indices : torch.Tensor
    A tensor of head index predictions of shape (batch_size, timesteps).
  • predicted_labels : torch.Tensor
    A tensor of arc label predictions of shape (batch_size, timesteps).
  • gold_indices : torch.Tensor
    A tensor of the same shape as predicted_indices.
  • gold_labels : torch.Tensor
    A tensor of the same shape as predicted_labels.
  • mask : torch.BoolTensor, optional (default = None)
    A tensor of the same shape as predicted_indices.


class AttachmentScores(Metric):
 | ...
 | def get_metric(self, reset: bool = False)


  • The accumulated metrics as a dictionary.


class AttachmentScores(Metric):
 | ...
 | def reset(self)