def encode_entities(
self,
entity_data: Dict[Text, Any],
precomputations: Optional[MessageContainerForCoreFeaturization],
bilou_tagging: bool = False,
) -> Dict[Text, List[Features]]:
"""Encode the given entity data.
Produce numeric entity tags for tokens.
Args:
entity_data: The dict containing the text and entity labels and locations
precomputations: Contains precomputed features and attributes.
bilou_tagging: indicates whether BILOU tagging should be used or not
Returns:
A dictionary of entity type to list of features.
"""
# TODO
# The entity states used to create the tag-idx-mapping contains the
# entities and the concatenated entity and roles/groups. We do not
# distinguish between entities and roles/groups right now.
if (
not entity_data
or not self.entity_tag_specs
or self.entity_tag_specs[0].num_tags < 2
):
# we cannot build a classifier with fewer than 2 classes
return {}
message = precomputations.lookup_message(user_text=entity_data[TEXT])
message.data[ENTITIES] = entity_data[ENTITIES]
if not message:
return {}
if bilou_tagging:
bilou_utils.apply_bilou_schema_to_message(message)
return {
ENTITY_TAGS: [
model_data_utils.get_tag_ids(
message, self.entity_tag_specs[0], bilou_tagging
)
]
}
def encode_entities(
self,
entity_data: Dict[Text, Any],
interpreter: NaturalLanguageInterpreter,
bilou_tagging: bool = False,
) -> Dict[Text, List["Features"]]:
"""Encode the given entity data with the help of the given interpreter.
Produce numeric entity tags for tokens.
Args:
entity_data: The dict containing the text and entity labels and locations
interpreter: The interpreter used to encode the state
bilou_tagging: indicates whether BILOU tagging should be used or not
Returns:
A dictionary of entity type to list of features.
"""
# TODO
# The entity states used to create the tag-idx-mapping contains the
# entities and the concatenated entity and roles/groups. We do not
# distinguish between entities and roles/groups right now.
if (not entity_data or not self.entity_tag_specs
or self.entity_tag_specs[0].num_tags < 2):
# we cannot build a classifier with fewer than 2 classes
return {}
message = interpreter.featurize_message(Message(entity_data))
if not message:
return {}
if bilou_tagging:
bilou_utils.apply_bilou_schema_to_message(message)
return {
ENTITY_TAGS: [
model_data_utils.get_tag_ids(message, self.entity_tag_specs[0],
bilou_tagging)
]
}
