search

dmis-lab / bern

A neural named entity recognition and multi-type normalization tool for biomedical text mining
https://bern.korea.ac.kr
BSD 2-Clause "Simplified" License
173 stars 44 forks source link

Using pre-trained models directly to predict on example text #10

Closed Lahssiniabdel closed 4 years ago

Lahssiniabdel commented 4 years ago

Hello, thank you for this great and very useful project.

I am a machine learning student, but I am not used to work with the first version of tensorflow. I am trying to use your pre-trained model for NER (I want to recognize diseaes, drugs and genes) instead of using your code to setup the API server.

So I downloaded your pre-trained model in the pretrainedBERT folder, but I don't know how to upload the file model.ckpt for each type of named entities and especially how to use it to predict on a text example.

Can you please enlighten me on this point?

Many thanks in advance for your help !

donghyeonk commented 4 years ago

Thank you for your interest.

For BioBERT NER, you might want to look here.

Have a nice day!