David Wadden comments

Results 27 comments of


                                            David Wadden

About train.py

Training code is now working! See [here](https://github.com/dwadden/multivers/blob/main/doc/training.md) for details. let me know if you've got more questions.

Hi, I'm sorry for the delay responding. I've added a section to the README covering this, see here: https://github.com/dwadden/multivers#making-predictions-for-new-datasets. Let me know if you've still got questions! Dave

Using your own data

Re your question about feeding generated abstracts line-by-line, this an interesting question. Seems like there's two obvious ways to do this: - Just treat the whole generated abstract as the...

Using your own data

@griff4692 are you good for me to close this?

Using your own data

No worries, thanks for closing. And sure, I'd gladly accept a PR to do single sentence scoring!

Adapting dataset for pre-train

Hi, Apologies that I've been so slow on providing the pretraining data. I'll try to get things posted in the next few weeks. Dave

Adapting dataset for pre-train

Hi, Training code is added now. See [here](https://github.com/dwadden/multivers/blob/main/doc/training.md) for details. Let me know if you've got more questions! Dave

TypeError: CorefResolver.make_output_human_readable: return type `None` is not a `typing.Dict[str, torch.Tensor]`.

Hi, The DyGIE / Spacy interface was added by @e3oroush. I unfortunately can't offer support, but maybe Ebi can help. Dave

TypeError: CorefResolver.make_output_human_readable: return type `None` is not a `typing.Dict[str, torch.Tensor]`.

Thanks!