shlomihod / deep-text-eval

Differnable Readability Measure Regularizer for Neural Network Automatic Text Simplification
24 stars 7 forks source link

Regularization for what? #36

Open shlomihod opened 6 years ago

shlomihod commented 6 years ago
  1. Kuan et al. repo: https://github.com/srewai/explicharr

  2. They have two working baselines:

    • ByteNet (character level)
    • Transformer (word level)

Let's use the Transformer because word level is easier to extract features - it is basically multiplying on a metrics! At least for the RS features, on POS we still need to work, but we can make first approximation on the distribution of different POS to a given word.