Sebastian Martschat

+1 for google scholar

If I understand you correctly, you want to take a model as input, and then initialize training on new data with that model. Is that what you want to do?

That's not implemented, but the code can be adapted. Unfortunately, I will not be able to have a closer look at this during this week. If you want to do...

The constructor of [perceptrons.pyx](https://github.com/smartschat/cort/blob/master/cort/coreference/perceptrons.pyx) has `priors` and `weights` parameters. However, for training, these are overwritten in the `fit` method. You need to make this overwriting optional, for example by adding...

Hi Rakesh, training the ranking model takes around two minutes per epoch. Preprocessing takes ~ 20 minutes if I remember correctly. Due to high memory requirements I train the models...

Can you isolate (and post) the document which causes the error message?

I did some debugging, the first example is tokenized as `['Contact', 'for', 'company', ':', 'Sven', 'Svensson', '212Â\xa0584Â\xa05242', '[email protected]', '.']`. I suspect that the `TypeError` happens because some representation I rely...