Stories are not working properly

I have created 3 forms of ordering a pizza, pasta and ice cream. Forms and extraction of entities are working fine. After form submission i have created denial paths of all three. Model is getting confused and opening ice cream form every time when we deny a request of pizza or pasta. I am sharing my rule.yml, stories.yml and config.yml file.

rule.yml version: “3.1”

rules:

  • rule: Say goodbye anytime the user says goodbye steps:

    • intent: goodbye
    • action: utter_goodbye
  • rule: Say ‘I am a bot’ anytime the user challenges steps:

    • intent: bot_challenge
    • action: utter_iamabot
  • rule: Activate Form pizza steps:

    • intent: inform_pizza
    • action: order_pizza_form
    • active_loop: order_pizza_form
  • rule: Submit form pizza condition:

    • active_loop: order_pizza_form steps:
    • action: order_pizza_form
    • active_loop: null
    • slot_was_set:
      • requested_slot: null
    • action: utter_order_details_pizza
    • action: utter_confirm_order
  • rule: Activate Form pasta steps:

    • intent: pasta_order
    • action: order_pasta_form
    • active_loop: order_pasta_form
  • rule: Submit form pasta condition:

    • active_loop: order_pasta_form steps:
    • action: order_pasta_form
    • active_loop: null
    • slot_was_set:
      • requested_slot: null
    • action: utter_order_details_pasta
    • action: utter_confirm_pasta
  • rule: Activate Form icecream steps:

    • intent: inform_icecream
    • action: order_icecream_form
    • active_loop: order_icecream_form
  • rule: Submit form pizza condition:

    • active_loop: order_icecream_form steps:
    • action: order_icecream_form
    • active_loop: null
    • slot_was_set:
      • requested_slot: null
    • action: utter_order_details_icecream
    • action: utter_confirm_icecream
  • rule: utter welcome message anytime in the conversation steps:

    • intent: thank_you
    • action: utter_welcome_message

stories.yml version: “3.1”

stories:

  • story: greet path steps:

    • intent: greet
    • action: utter_greet
  • story: place an order path steps:

    • intent: place_order
    • action: utter_order_details
  • story: Submit pizza form with confirmation path steps:

    • action: utter_confirm_order
    • intent: affirm
    • action: utter_thank_you
    • action: action_reset_all_slots
  • story: confirmation of submission denied of pizza path steps:

    • action: utter_confirm_order
    • intent: deny
    • action: utter_confirm_sure
    • intent: affirm
    • action: action_reset_all_slots
    • action: order_pizza_form
    • active_loop: order_pizza_form
  • story: pasta confirmation path steps:

    • action: utter_confirm_pasta
    • intent: affirm
    • action: utter_thank_you
    • action: action_reset_all_slots
  • story: pasta confirmation denied path steps:

    • action: utter_confirm_pasta
    • intent: deny
    • action: utter_confirm_sure
    • intent: affirm
    • action: action_reset_all_slots
    • action: order_pasta_form
    • active_loop: order_pasta_form
  • story: icecream confirmation path steps:

    • action: utter_confirm_icecream
    • intent: affirm
    • action: utter_thank_you
    • action: action_reset_all_slots
  • story: confirmation denied icecream path steps:

    • action: utter_confirm_icecream
    • intent: deny
    • action: utter_confirm_sure
    • intent: affirm
    • action: action_reset_all_slots
    • action: order_icecream_form
    • active_loop: order_icecream_form

config.yml

The config recipe.

Model Configuration

recipe: default.v1

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: 200 constrain_similarities: true
  • name: “CRFEntityExtractor”
  • name: EntitySynonymMapper
  • name: ResponseSelector epochs: 200 constrain_similarities: true
  • name: FallbackClassifier threshold: 0.3 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: MemoizationPolicy
  • name: RulePolicy
  • name: UnexpecTEDIntentPolicy max_history: 5 epochs: 200
  • name: TEDPolicy max_history: 5 epochs: 200 constrain_similarities: true