Regularization for what?

[shlomihod]

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.