MACHINE LEARNING BASED NLP

Synopsis: 

• SparkNLP 
• Working with SpacyML 
• Understanding BERT, ELMO and other embeddings 
• Deep learning framework (Tensorflow, Keras, and Pytorch) 
• Working with CRF, RNN, CNN and (BI)LSTM 
• Backpropagation 
• Basic Activation functions – Linear, Sigmoid, ReLu, Softmax 
• Basic Loss functions – Cross Entropy, RMSE, MAE. 

Resources: 

• Deep learning  
• https://www.youtube.com/watch?v=tpCFfeUEGs8&list=WL&index=7 
• https://www.coursera.org/learn/sequence-models-in-nlp 
• https://www.geeksforgeeks.org/named-entity-recognition/ 
• https://www.frontiersin.org/articles/10.3389/fcell.2020.00673/full – research paper 
• Word embedding 
• BERT embedding 
• GLOVE embedding 
• https://drive.google.com/file/d/1tpL4nytANEB63CKUbGZ6222KkEcaB-ne/view?usp=sharing – Natural Language Processing with Python by Steven Bird, Ewan Klein, and Edward Loper  
• https://drive.google.com/file/d/16DSsjhUoCBfoA395g6kiGFEE9eke5W7C/view?usp=sharing –  Fundamentals of Clinical Data Science by Pieter Kubben, Michel Dumontier, Andre Dekker  
• https://drive.google.com/file/d/1289hEauY37xHKWdP53L6r6SECSI5pTXK/view?usp=sharing – Natural Language Annotation for Machine Learning by James Pustejovsky and Amber stubbs