dialoguekit.nlu.models.intent_classifier_cosine

Implements intent classification based on cosine similarity.

Classes

IntentClassifierCosine

Cosine Intent classifier.

Module Contents

class dialoguekit.nlu.models.intent_classifier_cosine.IntentClassifierCosine(intents: List[dialoguekit.core.intent.Intent])

Bases: dialoguekit.nlu.intent_classifier.IntentClassifier

Cosine Intent classifier.

Parameters:

intents – Allowed intents.

train_model(utterances: List[dialoguekit.core.utterance.Utterance], labels: List[dialoguekit.core.intent.Intent]) → None

Trains a model based on a set of labeled utterances.

Parameters:

• utterances – List of Utterance instances.

• labels – List of associated intent labels.

classify_intent(utterance: dialoguekit.core.utterance.Utterance) → dialoguekit.core.intent.Intent

Classifies the utterance’s intent.

Classifies the intent of an utterance based on cosine similarity of TF-IDF-weighted term vectors.

Parameters:

utterance – An utterance.

Returns:

Predicted intent.

save_model(file_path: str) → None

Saves the trained model to a file.

This method uses the joblib library to save the model.

Parameters:

file_path – File path.

load_model(file_path: str) → None

Loads a model from a file.

This method uses the joblib library to load the model.

Parameters:

file_path – File path.