Mandar Joshi

Apologies for the late response. IIRC, I don't think I changed that part of the code from e2e-coref. You could be right, though. At a quick glance, it would seem...

Right. The `bucket_distance ` function will mask out the negative values.

Maybe? I suspect it doesn't matter since the slow scores are doing the heavy lifting. Happy to accept a PR though if you're seeing an improvement with that change :)

I haven't used the notebook, so I might be missing something. If I understand this right, you're trying to convert the `jsonlines` output of `predict.py`. Perhaps, you could directly use...

Yeah that's correct. The specific lines you need should be something like this: ``` Use standard file APIs to check for files with this prefix. Loaded 343 eval examples. Predicted...

I see. I'm not quite sure why you're getting the output in the jsonlines file but not the tmp file. I can't think of anything that's obviously wrong. Have you...

Thanks for your interest, Ehsan. I'm not sure I understand the choices you're thinking about. The pre-trained SpanBERT model can only encode documents up to 512 tokens in a single...

If you want to use this for QA/NLP with allennlp, see this https://github.com/mandarjoshi90/pair2vec#using-pretrained-pair2vec-embeddings If you want to do this in your own code, please see how it's initialized here. https://github.com/mandarjoshi90/pair2vec/blob/master/endtasks/bidaf_pair2vec.py#L72