utkarshminhas / LegalNER

Legal Text Annotation and Entity Recognition (Project for Applied Machine Learning in Computational Linguistics course at Indian University, Bloomington)

To build corpus

1. Keep TSV data files in the same folder as the MLCL - Project - Corpus.ipynb

2. The notebook would create a file train.txt in the path data_folder = './project/example/ner/test/'

   This would be the corpus to be used in the MLCL_Project.ipynb file.

To train model

1. Keep train.txt in the same folder as the file MLCL_Project.ipynb
2. The resultant model files (training.png, best-model.pt) will be in the path ./project/example/ner