/Named-Entity-Recognition

Primary LanguageJupyter Notebook

Anaconda Version: conda 4.12.0 Python Version: Python 3.9.7

Libraries required:

  • nltk
  • pandas
  • numpy
  • matplotlib
  • pickle
  • re
  • scikit learn
  • transformers
  • seqeval[gpu]
  • sentencepiece
  • torch

Make sure you have the following packages installed in your system in order to run the project

Workflow/steps to run:

Datasets:

https://drive.google.com/file/d/1AqZMqkAGUK7P-X_jXB9OddDJStTTUHE2/view?usp=sharing

  1. Upload the given notebook in Google Colab, choose 'GPU' in resources, and Run all the cells.
  2. It will take 10-15 minutes for the model to train and give results on the training, validation and test sets
  3. The notebook can be accessed directly at https://colab.research.google.com/drive/1JIghxsUBGTXe8bmg2kuEIS2n4pmE3wtH?usp=sharing
  4. References:
    1. https://www.freecodecamp.org/news/getting-started-with-ner-models-using-huggingface/
    2. https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/BERT Custom_Named_Entity_Recognition_with_BERT_only_first_wordpiece.ipynb
    3. https://skimai.com/how-to-fine-tune-bert-for-named-entity-recognition-ner/

Please be patient while running the codes. This assignment involved a lot of cpu/gpu/tpu intensive processing. Thank you.