kentonl / e2e-coref

End-to-end Neural Coreference Resolution
Apache License 2.0
524 stars 173 forks source link

Cannot reproduce the best results from the provided pretrained model #96

Open WinterShiver opened 3 years ago

WinterShiver commented 3 years ago

I have successfully loaded the pretrained weights from e2e-coref.tgz and get 72.39 on the test set. According to your NAACL18 paper paper, this corresponds to "e2e + ELMo + hyperparameter tuning"? I am wondering that how to reproduce the results of "+ c2f inference" and "+ second-order inference"? Could you please provide the corresponding configures of these two settings? Waiting for your apply.