Transformer Embedding Dialogue (TED) Policy is described in
This policy has a pre-defined architecture, which comprises the
- concatenate user input (user intent and entities), previous system actions,
slots and active forms for each time step into an input vector to
pre-transformer embedding layer;
- feed it to transformer;
- apply a dense layer to the output of the transformer to get embeddings of a
dialogue for each time step;
- apply a dense layer to create embeddings for system actions for each time
- calculate the similarity between the dialogue embedding and embedded system
actions. This step is based on the StarSpace
| __init__(featurizer: Optional[TrackerFeaturizer] = None, priority: int = DEFAULT_POLICY_PRIORITY, max_history: Optional[int] = None, model: Optional[RasaModel] = None, zero_state_features: Optional[Dict[Text, List["Features"]]] = None, **kwargs: Any, ,) -> None
Declare instance variables with default values.
| train(training_trackers: List[TrackerWithCachedStates], domain: Domain, interpreter: NaturalLanguageInterpreter, **kwargs: Any, ,) -> None
Train the policy on given training trackers.
| predict_action_probabilities(tracker: DialogueStateTracker, domain: Domain, interpreter: NaturalLanguageInterpreter, **kwargs: Any, ,) -> List[float]
Predict the next action the bot should take.
Return the list of probabilities for the next actions.
| persist(path: Union[Text, Path]) -> None
Persists the policy to a storage.
| load(cls, path: Union[Text, Path]) -> "TEDPolicy"
Loads a policy from the storage.
Needs to load its featurizer