language: "en"

pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: CRFEntityExtractor
  - name: EntitySynonymMapper
  - name: CountVectorsFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: "char_wb"
    min_ngram: 1
    max_ngram: 4
  - name: DIETClassifier