Jan-Christoph Klie

Hi, I honestly do not want to support adapters anymore because there are some issues with them for using in an external recommender, mainly that things like tagset are not...

If using external recommender does not work for you, then you could also use preannotation similarly to what we describe in https://colab.research.google.com/github/inception-project/inception/blob/master/notebooks/using_pretokenized_and_preannotated_text.ipynb . Then, your annotators would need to delete...

We need to wait for https://github.com/Adapter-Hub/adapter-transformers/issues/63 before making it more configurable.

This repository is deprecated, the new version is in https://github.com/inception-project/inception-external-recommender . There is also an example for sentence classification.

Thank you for your interest! It might be simple, but there are things that need to be taken into account: do you reload the pretrained model from spacy and retrain...

If you want to really do that, then you can fix the layers except the one you want to train: https://keras.io/getting-started/faq/#how-can-i-freeze-keras-layers . A guide in tensorflow might be http://cmgreen.io/2016/01/04/tensorflow_deep_autoencoder.html ,...

An example how to call them can be found in *main.py*.

Thank you for the request! How do you imagine would the card in the editor then look like? I would just imagine that you have a field configured, if it...

I added a prototype. You can see it [here](https://i.gyazo.com/8e32e254cf4e3f11b6a9ad8cb8e75712.mp4). Is this what you envisioned?

You should normally only have Maobi activated for cards types that actually have the field and have the field filled. How exactly do you get the error?