I need two classifiers and one NLU pipeline.
- name: WhitespaceTokenizer
- name: LanguageModelFeaturizer
- name: FaissClassifier
- name: DIET
For this example i train DIET classifier on intents started with “diet_” prefix (e.g. diet_hello). And FaissClassifier trains on intents started with faiss prefix.
- intent: faiss_skill_cities
- run game cities
- lets play in cities game
- go play a game cities
- intent: diet_hello
- good morning
I want to separate my nlu data to train different classifiers on different data
nlu result stay as before:
intent_ranking = sorted(knn_intent_ranking + diet_intent_ranking)
intent = intent_ranking
So my question - are the any other workaround to do the same?