config.yml

version: "3.1"
language: en
pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: CountVectorsFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: "char_wb"
    min_ngram: 1
    max_ngram: 4
  - name: DIETClassifier
    epochs: 100
  - name: FallbackClassifier
    threshold: 0.7
  - name: DucklingEntityExtractor
    url: http://localhost:8000
    dimensions:
    - amount-of-money
    - time
    - number
  - name: SpacyNLP
    model: "en_core_web_md"
    case_sensitive: false
  - name: "SpacyEntityExtractor"
    # Note: It is not possible to use the SpacyTokenizer + SpacyFeaturizer in
    #       combination with the WhitespaceTokenizer, and as a result the
    #       PERSON extraction by Spacy is not very robust.
    #       Because of this, the nlu training data is annotated as well, and the
    #       DIETClassifier will also extract PERSON entities .
    dimensions: ["PERSON"]
  - name: EntitySynonymMapper
policies:
- name: AugmentedMemoizationPolicy
- name: TEDPolicy
  epochs: 40
- name: RulePolicy
  core_fallback_threshold: 0.4
  core_fallback_action_name: "action_default_fallback"
  enable_fallback_prediction: True