COVID-19 Update

Visit our COVID update page.

Natural Language Processing | AISV.801

Natural Language Processing | AISV.801

This advanced three-segment course introduces students to many aspects of natural language processing (NLP), the artificial intelligence component of using human languages to interact with computers. We will start with an overview of NLP, natural language understanding (NLU), and natural language generation (NLG), and discuss algorithms such as:
  • the bag-of-words (BoW) model
  • word2vec
  • n-grams
  • skip-grams

Students will learn about: term frequency (tf), inverse document frequency (idf), and tf-idf.

In addition, you will learn about recommendation systems, sentiment analysis, and document classification. In the second portion of the course, you will be introduced to deep learning (DL) and how DL and NLP can be combined. We will look at the success of convolutional neural networks (CNNs) in solving NLP tasks and the popularity of architectures that use bidirectional long short-term memory (LSTM), an artificial recurrent neural network (RNN) architecture, to solve NLP tasks, such as search.

In the third portion of this course we explore reinforcement learning (RL) and deep reinforcement learning, learning how to combine deep RL and NLP. These combined technologies have improved state-of-the-art natural language processing and reinforcement learning, and contributed to the progress in a plethora of other fields. You will also learn about the Transformer architecture that has revolutionized NLP, followed by language models in the BERT family. Moreover, you will learn about the amazing GPT-3 language model that can generate functional Web pages, blog posts, and even poetry mimicking Shakespeare and Edgar Allen Poe. Relevant Python-based code samples for these language models are included."

After completing this course, you can continue your study of NLP to acquire a deeper understanding of NLP and more sophisticated combinations of NLP with other branches of machine learning and with deep reinforcement learning.

Learning Outcomes
At the conclusion of the course, you should be able to

  • Describe the purpose of NLU and NLG
  • Explain tf, idf, and tf-idf
  • Describe BoW, word2vec, and Glove
  • Explain how n-grams and skip-grams work
  • Describe how bi-LSTM differs from a standard LSTM
  • Explain how bi-LSTMs used in NLP tasks
  • Describe the ELMo and BERT architectures
  • Discuss the advantages/disadvantages of RL
  • Identify the purpose of the Bellman equation
  • Describe Q-Learning, models, and policies
  • Explain how NLP is combined with Deep RL

Students are required to bring Laptops for classroom work.

Skills Needed: Moderate level of computer programming ability in Python, comfortable with an editor, familiarity with basic command-line operations on a laptop, and a good understanding of Machine Learning models and Deep Learning models.

Note(s): Students are required to bring laptops for classroom work. The code samples use Python 3.6.8 and TensorFlow 2/Keras, along some Jupyter notebooks in Google Colaboratory (students can optionally pre-register for a free account).  Students also have the option of installing the Python 3+ version of Anaconda distribution on their laptops from the following link: on their machines.

Have a question about this course?
Speak to a student services representative.
Call (408) 861-3860
This course is related to the following programs:


Estimated Cost: $1195

Course Availability Notification

Please use this form to be notified when this course is open for enrollment.

Contact Us
Speak to a student services representative.

Call (408) 861-3860