dialoguekit.nlu.intent_classifier
=================================

.. py:module:: dialoguekit.nlu.intent_classifier

.. autoapi-nested-parse::

   Abstract interface for intent classification.

   This interface assumes a single intent per utterance, i.a., approaches
   the task as a single-label classification problem. The generalization to
   multi-label classification is left to future work.



Classes
-------

.. autoapisummary::

   dialoguekit.nlu.intent_classifier.IntentClassifier


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

.. py:class:: IntentClassifier(intents: List[dialoguekit.core.intent.Intent])

   Bases: :py:obj:`abc.ABC`


   Initializes the intent classifier.

   :param intents: List of allowed intents.


   .. py:method:: train_model(utterances: List[dialoguekit.core.utterance.Utterance], labels: List[dialoguekit.core.intent.Intent]) -> None
      :abstractmethod:


      Trains a model based on a set of labeled utterances.

      :param utterances: List of Utterance instances.
      :param labels: List of associated intent labels.

      :raises NotImplementedError: If not implemented in derived class.



   .. py:method:: classify_intent(utterance: dialoguekit.core.utterance.Utterance) -> dialoguekit.core.intent.Intent
      :abstractmethod:


      Classifies the intent of an utterance.

      :param utterance: An utterance.

      :returns: Predicted intent.

      :raises NotImplementedError: If not implemented in derived class.



   .. py:method:: save_model(file_path: str) -> None
      :abstractmethod:


      Saves the trained model to a file.

      :param file_path: File path.

      :raises NotImplementedError: If not implemented in derived class.



   .. py:method:: load_model(file_path: str) -> None
      :abstractmethod:


      Loads a model from a file.

      :param file_path: File path.

      :raises NotImplementedError: If not implemented in derived class.