Saber is a deep-learning based tool for information extraction in the biomedical domain. Pull requests are welcome! Note: this is a work in progress. Many things are broken, and the codebase is not stable.
To decide whether to use this library it would be good to see NER and entity linking level metrics for the different pretrained models.
From the google colab the section describing pretrained models wasn't helpful it sent me here: https://baderlab.github.io/saber-api-docs/#introduction where it was good that the entity linking namespace was exposed but performance for NER and entity linking were missing.
For my use case exposing model performance and making this visible would be very useful.
Unfortunately (and at least for the time being, this could change) I am no longer working on the library. I realized that better solutions exist for my use cases (AllenNLP or SpaCy being examples).
JohnGiorgi
commented
4 years ago
To decide whether to use this library it would be good to see NER and entity linking level metrics for the different pretrained models.
From the google colab the section describing pretrained models wasn't helpful it sent me here: https://baderlab.github.io/saber-api-docs/#introduction where it was good that the entity linking namespace was exposed but performance for NER and entity linking were missing.
For my use case exposing model performance and making this visible would be very useful.