No Description

Tolstoyevsky f7a56eceb0 Merge remote-tracking branch 'origin/master' 2 months ago
.dvc 1a2517aa68 Added a dvc stage to download data from gdrive 2 months ago
data f7a56eceb0 Merge remote-tracking branch 'origin/master' 2 months ago
model dfdc2fb905 model_params.json is now a dvc output 2 months ago
notebooks f7a56eceb0 Merge remote-tracking branch 'origin/master' 2 months ago
python 4a7abafeac Straighten out imports for gorenml 2 months ago
templates b26b03ff09 Adding flask server 6 months ago
.gitignore 19bb546f82 Adding PyCharm files to gitignore 3 months ago ea99ff171c Update 2 months ago
requirements.txt 8d050f4196 Adding matplotlib to requirements 2 months ago ab36accf3f Import fixes in and 2 months ago

Data Pipeline

DVC Managed File
Stage File
Code File

Named-Entity-Recognition Workshop

In this workshop, we would learn how to automatically style ( bold , Italics, etc. ) a word according to context.

We learn styling from html files automatically and apply them to raw text.

This project is used mainly to demonstrate deep-learning implementation of named-entity-recognition (NER) models.

Preparing a Google Colab environment

Recommended: training is about x10 faster than a local environment
  1. Google Colab notebooks (and other resources) are located in Google Drive under Colab Notebooks directory.
    If you are using Colab for the first time, open Colab and save one of the example notebooks. The notebook will be saved to Colab Notebooks directory.
  2. Upload folder (repo content + data zip file) to your Google Drive. Make sure nlp_ner_workshop folder is located in your Colab Notebooks folder.
    Due to Google Drive quota issues make sure not to unzip the data file.
  3. Open one of the example notebooks, change the GOOGLE_COLAB to True, and run all to test it.
  4. You might need to configure your Runtime type to Python 3 and set the Hardware accelerator to GPU. Both located in Runtime=>Change runtime type.

Preparing a local environment

Note: in case you are not using Colab
  1. Make sure Python3 is installed.
  2. You can create a virtual environment (recommended) using python3 -m virtualenv ner_ws
  3. To activate your virtual env, run: source ner_ws/bin/activate
  4. Now install all of the requirements: pip3 install -r requirements.txt[](

Training a model

  1. Download data from our Google drive
  2. Save the .zip file in the data/ folder.
  3. Run to train an NER model.
  4. Run to evaluate your model in the browser.

For more details, contact me at .