How do you determine what is the best config scheme to use?

Rasa Open Source
1

How do you know what combination gives the best result in your config?

This is my current configuration, I have dataset with only english language and a lot frequently asked questions.

Any tips how to check if I can make a better combination?

language: "en"
pipeline:
- name: "WhitespaceTokenizer"
- name: "ConveRTFeaturizer"
- name: "CountVectorsFeaturizer"
- name: "EmbeddingIntentClassifier"
- name: "ResponseSelector"

# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
  - name: MemoizationPolicy
  - name: EmbeddingPolicy
    max_history: 5
    epochs: 100
  - name: MappingPolicy