soap opera LSTM?

[bnicenboim]

Hi, one year later me again looking at your paper (Single-Stage Prediction Models Do Not Explain the
Magnitude of Syntactic Disambiguation Difficulty) :)

It seems that the soap opera LSTM got the best results, right? do you happen to have the pre-trained model available?

By the way, interestingly, the surprisal values from GPT2 were useless! (They aren't with many other datasets).