Return logits/score/probabilities from the coref Model

[utkarsh-fileread]

Is your feature request related to a problem? Please describe.
I wrote a coreference resolver based on my requirements using the coref model as base to create clusters. Sometimes in tricky sentences, the clusters are not optimal.

Describe the solution you'd like
It would be great if the pipeline also returned a membership score which tells how likely does this particular phrase belongs to a cluster.

Describe alternatives you've considered
N/A

Additional context
N/A