dialoguekit.nlg.template_from_training_data
===========================================

.. py:module:: dialoguekit.nlg.template_from_training_data

.. autoapi-nested-parse::

   Extract user response utterance templates from annotated training data.



Functions
---------

.. autoapisummary::

   dialoguekit.nlg.template_from_training_data.build_template_from_instances
   dialoguekit.nlg.template_from_training_data.extract_utterance_template


Module Contents
---------------

.. py:function:: build_template_from_instances(utterances: List[dialoguekit.core.annotated_utterance.AnnotatedUtterance]) -> Dict[str, List[dialoguekit.core.annotated_utterance.AnnotatedUtterance]]

   Builds the NLG template.

   The dialogue acts from the utterances will be used to build the templates.
   If an utterance has multiple dialogue acts, the intents will be concatenated
   with a semicolon. If an utterance does not have any dialogue acts, it will
   be skipped.

   :param utterances: List of utterances to build the template from.

   :returns: Dictionary with intents as keys and lists of corresponding templates.


.. py:function:: extract_utterance_template(annotated_dialogue_file: str, participant_to_learn: str = 'USER', satisfaction_classifier: Optional[Union[None, dialoguekit.nlu.models.satisfaction_classifier.SatisfactionClassifier]] = None) -> Dict[str, List[dialoguekit.core.annotated_utterance.AnnotatedUtterance]]

   Extracts utterance templates for each intent.

   If a Satisfaction Classifier is provided it will be used to classify the
   utterances. The classification logic is as follows:

       - Hold participant utterance.
       - Hold counter-participant utterance.
       - Concatenate participant and counter-participant utterance and
         classify satisfaction.
       - The next utterance from participant will be given the satisfaction
         from the concatenated utterance from the previous utterances.
         reflecting the satisfaction at that given point in time.

   :param annotated_dialog_file: Annotated dialogue json file.
   :param participant_to_learn: Which participant we want to create a template on.
   :param satisfaction_classifier: SatisfactionClassifier.

   :returns: Dictionary with intents as keys and lists of corresponding templates.