Choosing a Pipeline

In Rasa Open Source, incoming messages are processed by a sequence of components. These components are executed one after another in a so-called processing pipeline defined in your config.yml. Choosing an NLU pipeline allows you to customize your model and finetune it on your dataset.

• How to Choose a Pipeline

  • The Short Answer

    If your training data is in English, a good starting point is the following pipeline:

    language: "en"
    
    pipeline:
      - name: ConveRTTokenizer
      - name: ConveRTFeaturizer
      - 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
    

    If your training data is not in English, start with the following pipeline:

    language: "fr"  # your two-letter language code
    
    pipeline:
      - 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
    

• A Longer Answer

  We recommend using the following pipeline if your training data is in English:

  language: "en"
  
  pipeline:
    - name: ConveRTTokenizer
    - name: ConveRTFeaturizer
    - 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
  

  The pipeline contains the ConveRTFeaturizer that provides pre-trained word embeddings of the user utterance, which is especially useful if you don’t have enough training data.

• Choosing the Right Components

  A pipeline usually consists of three main parts:

  • Tokenization
  • Featurization
  • Entity Recognition / Intent Classification / Response Selectors

Tokenization

For tokenization of English input, we recommend the ConveRTTokenizer.

Featurization

You need to decide whether to use components that provide pre-trained word embeddings or not. We recommend using them in cases of small amounts of training data. Once you have larger amounts of data, supervised embeddings can make your model more specific to your domain.

Multi-Intent Classification

You can use Rasa Open Source components to split intents into multiple labels by using the DIETClassifier in your pipeline.

Comparing Pipelines

Rasa gives you the tools to compare the performance of multiple pipelines directly. See Comparing NLU Pipelines for more information.

Handling Class Imbalance

Classification algorithms often do not perform well with a large class imbalance. To mitigate this, you can use a balanced batching strategy which ensures that all classes are represented in every batch.