"NLU_fallback" happening even when the example is present in train set

Rasa Open Source Feedback on Rasa Open Source
1

Rasa is giving " nlu_fallback as intent " even when the example is present in train set. For example-

> bot- Can we proceed ?
>user- yes

intent - nlu fallback

The example " yes" is present for the intent “user_proceed”.

the config file threshold settings are -

> # Configuration for Rasa NLU.
> # https://rasa.com/docs/rasa/nlu/components/
> recipe: default.v1
> 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 https://rasa.com/docs/rasa/tuning-your-model for more information.
> 
> 
>   - name: SpacyNLP
>     model: "en_core_web_md"
>     case_sensitive: False
>   - name: SpacyTokenizer
>   - name: SpacyFeaturizer
>   - name: RegexFeaturizer
>   - name: LexicalSyntacticFeaturizer
>   - name: CountVectorsFeaturizer
>   - name: CountVectorsFeaturizer
>     analyzer: "char_wb"
>     min_ngram: 1
>     max_ngram: 4
>   - name: DIETClassifier
>     epochs: 350
>   - name: FallbackClassifier
>     threshold: 0.7  
>     ambiguity_threshold: 0.1
>   - name: EntitySynonymMapper
>   - name: ResponseSelector
>     epochs: 350
> # 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 https://rasa.com/docs/rasa/policies for more information.
>    - name: MemoizationPolicy
>    - name: RulePolicy
>      core_fallback_threshold: 0.4
>      core_fallback_action_name: "action_default_fallback"
>      enable_fallback_prediction: True
>    - name: UnexpecTEDIntentPolicy
>      max_history: 5
>      epochs: 350
>    - name: TEDPolicy
>      max_history: 5
>      epochs: 350
>      constrain_similarities: True

What is this happening?

2

How many examples of the intent do you have?

3

Around 50 for each intent.

4

Do you have “yes” as an example of other intents?

5

“yes” is with other words in a sentence as example.

for eg -

         intent - customer_feedback
        example - yes madam, it is working
                  yes absolutely fine now