Franco Luque

I do. I will post it here soon.

Here is the code. Add an optional parameter finish, and only change the status to solved if finish=True. Drawback: the entire results must be provided each time. ``` def store_results(self,...

And here is a method `update_results` that allows updating only some sub-fields of the results field. ``` def update_results(self, booking_ticket, flat_results, finish=True): """ Same as store_results, but do not replace...

I see. At least, Django will allow subclassing. I am still interested in doing this, so I may be soon commenting on this.

This behaviour would be correct if we say IEPY must output facts (not necessarily evidence). Seed facts don't need evidence that justify them. However, I think IEPY focus is to...

Reproducing: > > > from iepy.tokenizer import en_tokenize_and_segment > > > s = u"The bleeding wasn't from a miscarriage and she still tests positive for pregnancy." > > > en_tokenize_and_segment(s)['tokens']...

Thanks for the quick answer! the examples are from a dataset.

thanks @AngledLuffa ! I was just pointing where I got the "liquid can" from, the dataset I have is not even tagged. Stanza is great!!

> I have a similar issue in Spanish for an incorrect POS tag. I recognize this is not likely a bug in Stanza but just the result of training against...

Hello. The preprocessing pipeline can be customized to introduce a different tokenizer. See for instance: https://github.com/awolfmann/PLN-2015/blob/practico4/information_extraction/resoluciones-unc/bin/preprocess.py