Some actions are not predicted accurate

Config.yml :-

Configuration for Rasa NLU.

Components

language: en

pipeline:

# No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.

# If you’d like to customize it, uncomment and adjust the pipeline.

# See Tuning Your NLU Model for more information.

  • name: WhitespaceTokenizer
  • name: RegexFeaturizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer
  • name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4
  • name: DIETClassifier epochs: 100
  • name: EntitySynonymMapper
  • name: ResponseSelector epochs: 100

- name: FallbackClassifier

threshold: 0.5

ambiguity_threshold: 0.1

Configuration for Rasa Core.

Policies

policies:

# No configuration for policies was provided. The following default policies were used to train your model.

# If you’d like to customize them, uncomment and adjust the policies.

# See Policies for more information.

  • name: FormPolicy
  • name: MemoizationPolicy max_history: 1
  • name: RulePolicy
  • name: TEDPolicy max_history: 3 epochs: 100

in this image: my intent is AssetMaintenance_WO_Details and entity: (‘WO_number’,) and the action is : Action_WorkOrder_Details : that are defined by me

And in this image: intent,entity and action changed because it not predict accurate action

in my RASA 2.0 chatbot,some of action are not predicted accurate . what should i do know ,modify my config file or something else? I’m new in RASA,Anyone can help me in this issue ?