This is an alpha version of what could become a named entity tagger and linker...
For lazy people, just clone repository and try this:
cat data/all.txt | python predict.py
Sorry but don't expect good results for the moment.
This requires quite standard packages installed, such as scikit.
If you'd like to learn a new model, you'll have to:
- have some annotated data
- find a corpus to learn embeddings
