Mandar Joshi

IIRC, I don't think I changed that part of the code from the original e2e-coref. Are you seeing this on English OntoNotes? Possibly related to https://github.com/mandarjoshi90/coref/issues/6 ?

Sorry about the late response. Here's the pipleline. `$gap_file_prefix` points to the path of the GAP file without the tsv prefix. `$vocab_file` refers to the cased BERT vocab file. ```...

1. I did not run the e2e-coref model. Looks like we copied from the wrong table for that row. I will amend the paper. We definitely evaluated on the test...

Not in this repo, no. But if you look at the output prediction files (*.jsonlines), you should be able to do this easily since it contains coreferent span clusters.

Not a trivial question at all. Thanks for your interest! The evaluation error is likely a product of the optimizer going off the rails. At a high level, I would...

Hmm this is quite odd. The `doc_key` is basically a genre embedding, and having a different set of genres should be fine. There are two learning rates -- one for...

From a quick glance, I think so. I suspect getting rid of it will mess up the evaluation, but you can still try it out. The official coref evaluation is...

Closing due to inactivity. Please feel free to reopen if something comes up. Thanks!

@fairy-of-9 Did you try training with that change? CCing @freesunshine0316 who might be interested.

I'm AFK for the weekend. Off the top of my head, one way would be to add an integer document ID to input_props. You can then print or tf.Print that...