Goal

• This repo contains an MXNet implementation of this state of the art entity recognition model.
• You can find my blog post on the model here.

Running the code

To reproduce the preprocessed training data:

1. Download and unzip the data: https://www.kaggle.com/abhinavwalia95/entity-annotated-corpus/downloads/ner_dataset.csv
2. Move ner_dataset.csv into ./data
3. $ cd src && python preprocess.py

To train the model:

• $ cd src && python ner.py

To run inference using trained model:

1. Recreate the bucketing module using sym_gen defined in ner.py
2. Loading saved parameters using module.set_params()

Refer to the test function in the Bucketing Module example and this issue on Bucketing Module Prediction