Bot is not following the story


The bot doesn’t follow the story, it jumps into the middle of the story.


  1. user wrote → stutter exercises [therapy_stutter_session_1_start] (where the story begins)
  2. bot response → Are you an overthinker? [utter_consider_confident] (in the middle of the story)

We’ve tried with different policies such as SklearnPolicy, KerasPolicy, but it keeps calling FallbackPolicy when the story ends. Also with TEDPolicy --augmentation 0 / max_history: 1 same problem occurs, jumps into the middle of the story.

We want the story to be followed as it is in declared in the, at the end of the story to know that story is ended and it can start from the beginning with a new story.

Our bot should give daily stutter exercises and tips to improve your speaking.


config.yml (452 Bytes) (1022 Bytes) (1.4 KB)

Looking at your logs, what intent is being identified in this user message? Is it therapy_stutter_session_1_start as expected?

When the user wrote “stutter exercises” the bot identifies the “utter_consider_confident” instead of " therapy_stutter_session_1_start"


It seems to work with the following configuration:

language: en pipeline:

  • name: “WhitespaceTokenizer”
  • name: “RegexFeaturizer”
  • name: “LexicalSyntacticFeaturizer”
  • name: “CountVectorsFeaturizer”
  • name: “CountVectorsFeaturizer” analyzer: “char_wb” min_ngram: 1 max_ngram: 4
  • name: “DIETClassifier”
  • name: “EntitySynonymMapper”


  • name: TEDPolicy max_history: 5 epochs: 200 batch_size: 50 max_training_samples: 300
  • name: FallbackPolicy
  • name: MemoizationPolicy
  • name: MappingPolicy
  • name: FormPolicy