Seems interesting! How can it be used with other languages than English?
FastText for example has pretrained embeddings for 294 languages: https://github.com/facebookresearch/fastText/blob/master/pre...
Google's Parsey McParseface handles POS tagging for 53 languages: https://github.com/tensorflow/models/blob/f87a58cd96d45de73c...
This current docker image is not exposing those other languages but I can expose them in an update if it helps a lot of people.
[1] https://spacy.io/usage/models [2] http://compling.hss.ntu.edu.sg/omw/