kentonl / e2e-coref

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

About pruning spans #87

Open zhiqihuang opened 4 years ago

zhiqihuang commented 4 years ago

Hi,

After reading the paper, I have a question about pruning spans.

In section 5, the framework prunes the candidate spans during both training and evaluation. I think during evaluation is reasonable since the weights for word vectors are tuned.

But during the early stage of training, the weights for word vectors are not learned (e.g., random initialized in the first epoch), could keeping top lambda*T spans ordered by mention scores discard potential valid mentions?

Thanks.