language: en pipeline: - name: WhitespaceTokenizer - name: RegexFeaturizer - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: "char_wb" min_ngram: 1 max_ngram: 4 - name: DIETClassifier epochs: 50 model_confidence: linear_norm constrain_similarities: True loss_type: cross_entropy