BiLSTM + CRF for NER

Before running anything, make sure you have generated the pre-processed dataset using the generate_data.py file with the command mentioned in the parent directory.

Additional Requirements

1. Packages: Anaconda, Pytorch, AllenNLP
2. Glove 300B embeddings

Training

1. Change settings in model/config.py
2. Main settings to change: File directories, model hyperparameters etc.

3. Run build_data.py

   • Builds embedding dictionary, text file of words, chars tags, as well as idx to word and idx to char mapping for the model to read

4. Run train.py

Results