var featurizeTextOptions = new TextFeaturizingEstimator.Options()
{
    // Produce cleaned tokens for input to the word embedding transform
    OutputTokensColumnName = "OutputTokens", 

    // Text cleaning (not shown is stop word removal)
    KeepDiacritics = true, // Non-default
    KeepPunctuations = false,
    KeepNumbers = false, // Non-default
    CaseMode = TextNormalizingEstimator.CaseMode.Lower,

    // Row-wise normalization (see: NormalizeLpNorm)
    Norm = TextFeaturizingEstimator.NormFunction.L2,

    // Use ML.NET's built-in stop word remover (non-default)
    StopWordsRemoverOptions = new StopWordsRemovingEstimator.Options() { Language = TextFeaturizingEstimator.Language.English },

    // ngram options
    WordFeatureExtractor = new WordBagEstimator.Options()
    {
        NgramLength = 2,
        UseAllLengths = true, // Produce both unigrams and bigrams
        Weighting = NgramExtractingEstimator.WeightingCriteria.Tf, // Can also use TF-IDF  or IDF
    },

    // chargram options
    CharFeatureExtractor = new WordBagEstimator.Options()
    {
        NgramLength = 3,
        UseAllLengths = false, // Produce only tri-chargrams and not single/double characters
        Weighting = NgramExtractingEstimator.WeightingCriteria.Tf, // Can also use TF-IDF  or IDF
    },
};

// Featurization pipeline
var pipeline = mlContext.Transforms.Conversion.MapValueToKey("Label", "Label") // Needed for multi-class to convert string labels to the Key type
    
    // Create ngrams, and cleaned tokens for the word embedding
    .Append(mlContext.Transforms.Text.FeaturizeText("FeaturesText", featurizeTextOptions, new[] { "InputText" })) // Use above options object

    // Word embedding transform reads in the cleaned tokens from the text featurizer
    .Append(mlContext.Transforms.Text.ApplyWordEmbedding("FeaturesWordEmbedding", 
        "OutputTokens", WordEmbeddingEstimator.PretrainedModelKind.FastTextWikipedia300D))

    // Feature vector is the concatenation of the ngrams from the text transform, and the word embeddings
    .Append(mlContext.Transforms.Concatenate("Features", new[] { "FeaturesText", "FeaturesWordEmbedding" }))

    // Enable if numeric features are also included. Normalization is generally unneeded if only using the output from FeaturizeText as it's row-wise normalized w/ a L2-norm; word embeddings are also well behaved.
    //.Append(mlContext.Transforms.NormalizeMinMax("Features", "Features"))

    // Cache the featurized dataset in memory for added speed
    .AppendCacheCheckpoint(mlContext);

// Trainer 
var trainer = mlContext.MulticlassClassification.Trainers.OneVersusAll(mlContext.BinaryClassification.Trainers.AveragedPerceptron(labelColumnName: "Label", numberOfIterations: 10, featureColumnName: "Features"), labelColumnName: "Label")
    .Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel", "PredictedLabel"));

var trainingPipeline = pipeline.Append(trainer);