Skip to content

A simple NLP-NER project for named entity recognition using character-level labeling and transformer-based token classification.

License

Notifications You must be signed in to change notification settings

warjohn/NLP-NER

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NLP-NER

The task of the project: search for an entity in a sentence, in this case, a product article. The BERT model was taken as a basis for additional training. Symbolic vectorization was used. And a tokenizer pre-trained from the same model.

Getting Started

  1. Create python-env and activate
python3 -m venv venv
source venv/bin/activate
  1. install dependences
pip install -r req.txt

Usage

  • File -> final.ipynb This file describes the process of training the model
  • File -> test.ipynb This file is about how to use the model in the future.
  • Dir -> ner_model contains model's checkpoints

License

This project is licensed under the [License Name] - see the LICENSE file for details.

Contacts

About

A simple NLP-NER project for named entity recognition using character-level labeling and transformer-based token classification.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published