The bot is not predicting correct action as per stories

Hi Everyone.

My chatbot is about storing details for purchase order and invoice. Intents are getting correctly classified but the action is getting wrong predicted. How can I make sure to let rasa core do predict correct action. For intent query_po_invoice, it is predicting action utter_tell_new_po_status

This is the stories.yml file.

  • story: greeting

    steps:

    • intent: greet

    • action: utter_greet

  • story: query invoice po

    steps:

    • intent: query_po_invoice

    • action: action_show_details

  • story: update invoice status

    steps:

    • intent: change_status

      entities:

      • invoice: invoice
    • action: utter_tell_new_invoice_status

    • checkpoint: check_status

  • story: update purchase order status

    steps:

    • intent: change_status

    • action: utter_tell_new_po_status

    • checkpoint: check_status

  • story: final step

    steps:

    • checkpoint: check_status

    • intent: affirm

    • action: action_update_status

this is nlu.yml file

Please share your config.yml as well. What policies you are using?

1 Like

Please find below config.yml file

Configuration for Rasa NLU.

https://rasa.com/docs/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: RegexEntityExtractor

    case_sensitive: False

    use_lookup_tables: True

    use_regexes: True

  • name: EntitySynonymMapper

  • name: ResponseSelector

    epochs: 100

  • name: FallbackClassifier

    threshold: 0.7

    ambiguity_threshold: 0.1

Configuration for Rasa Core.

https://rasa.com/docs/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: MemoizationPolicy

    max_history: 0

  • name: TEDPolicy

    max_history: 0

    epochs: 100

  • name: RulePolicy

    core_fallback_action_name: “action_default_ask_affirmation”