notice

This is documentation for Rasa Open Source Documentation v2.0.x, which is no longer actively maintained.
For up-to-date documentation, see the latest version (2.1.x).

Version: 2.0.x

rasa.nlu.extractors.extractor

EntityExtractor Objects

class EntityExtractor(Component)

filter_irrelevant_entities

| @staticmethod
| filter_irrelevant_entities(extracted: list, requested_dimensions: set) -> list

Only return dimensions the user configured

filter_trainable_entities

| filter_trainable_entities(entity_examples: List[Message]) -> List[Message]

Filters out untrainable entity annotations.

Creates a copy of entity_examples in which entities that have extractor set to something other than self.name (e.g. 'CRFEntityExtractor') are removed.

convert_predictions_into_entities

| convert_predictions_into_entities(text: Text, tokens: List[Token], tags: Dict[Text, List[Text]], confidences: Optional[Dict[Text, List[float]]] = None) -> List[Dict[Text, Any]]

Convert predictions into entities.

Arguments:

  • text - The text message.
  • tokens - Message tokens without CLS token.
  • tags - Predicted tags.
  • confidences - Confidences of predicted tags.

Returns:

Entities.

get_tag_for

| @staticmethod
| get_tag_for(tags: Dict[Text, List[Text]], tag_name: Text, idx: int) -> Text

Get the value of the given tag name from the list of tags.

Arguments:

  • tags - Mapping of tag name to list of tags;
  • tag_name - The tag name of interest.
  • idx - The index position of the tag.

Returns:

The tag value.

check_correct_entity_annotations

| @staticmethod
| check_correct_entity_annotations(training_data: TrainingData) -> None

Check if entities are correctly annotated in the training data.

If the start and end values of an entity do not match any start and end values of the respected token, we define an entity as misaligned and log a warning.

Arguments:

  • training_data - The training data.