namespace_swapping_field
allennlp.data.fields.namespace_swapping_field
NamespaceSwappingField#
class NamespaceSwappingField(Field[torch.Tensor]):
| def __init__(
| self,
| source_tokens: List[Token],
| target_namespace: str
| ) -> None
A NamespaceSwappingField
is used to map tokens in one namespace to tokens in another namespace.
It is used by seq2seq models with a copy mechanism that copies tokens from the source
sentence into the target sentence.
Parameters
- source_tokens :
List[Token]
The tokens from the source sentence. - target_namespace :
str
The namespace that the tokens from the source sentence will be mapped to.
index#
class NamespaceSwappingField(Field[torch.Tensor]):
| ...
| @overrides
| def index(self, vocab: Vocabulary)
get_padding_lengths#
class NamespaceSwappingField(Field[torch.Tensor]):
| ...
| @overrides
| def get_padding_lengths(self) -> Dict[str, int]
as_tensor#
class NamespaceSwappingField(Field[torch.Tensor]):
| ...
| @overrides
| def as_tensor(self, padding_lengths: Dict[str, int]) -> torch.Tensor
empty_field#
class NamespaceSwappingField(Field[torch.Tensor]):
| ...
| @overrides
| def empty_field(self) -> "NamespaceSwappingField"