Leveraging Deep Learning for Natural Language Processing Course

In this Natural Language Processing course, you will learn how to navigate the various text pre-processing techniques and select the best neural network architecture for Natural Language Processing.

Leveraging Deep Learning for Natural Language Processing Course Benefits

• In this course, you learn how to: 

  • Understand various pre-processing techniques for deep learning problems.
  • Build a vector representation of text using word2vec and GloVe.
  • Create a named entity recognizer and parts-of-speech tagger with Apache OpenNLP.
  • Build a machine translation model in Keras, a deep learning API.
  • Develop a text generation application using Long short-term memory (LSTM).
  • Build a trigger word detection application using an attention model.
  • Test your knowledge in the included end-of-course exam.
  • Continue learning and face new challenges with after-course one-on-one instructor coaching.

Natural Language Processing Course Outline

Module 1: Introduction to Natural Language Processing

In this module, you will learn about:

• The basics of Natural Language Processing and its applications
• Popular text pre-processing techniques
• Word2vec and Glove word embeddings Sentiment classification

Module 2: Applications of Natural Language Processing

In this module, you will learn about: 

• Named Entity Recognition and how to develop it using popular libraries
• Parts of Speech Tagging

Module 3: Introduction to Neural Networks

In this module, you will learn about:

• Basics of Gradient descent and backpropagation.
• Fundamentals of Deep Learning, Keras and deploying a Model-as-a-Service (MaaS)

Module 4: Foundations of Convolutional Neural Networks (CNN)

• In this module, you will learn about CNN architecture, application areas, and implementation using Keras.

Module 5: Recurrent Neural Networks (RNN)

• In this module, you will learn about RNN architecture, application areas, vanishing gradients, and implementation using Keras.

Module 6: Gated Recurrent Units (GRU)

• In this module, you will learn about GRU architecture, application areas, and implementation using Keras.

Module 7: Long Short-Term Memory (LSTM)

• In this module, you will learn about LSTM architecture, application areas, and implementation using Keras.

Module 8: State of the Art in Natural Language Processing

In this module, you will learn how to:

• Perform Attention Model and Beam search
• Use End to End models for speech processing
• Use Dynamic Neural Networks to answer questions

Module 9: A Practical NLP Project Workflow in an Organization

In this module, you will learn how to:

• Acquire data using free datasets and crowdsourcing
• Use cloud infrastructure, such as the Google collab notebook, to train deep learning NLP models
• Write a Flask framework server RestAPI to deploy a model
• Deploy the web service on cloud infrastructures such as Amazon Elastic Compute Cloud (Amazon EC2) or Docker Cloud
• Leverage the promising techniques in NLP, such as Bidirectional Encoder Representations from Transformers (BERT)