Great Learning is offering a free course on Text Summarization using BERT. It is designed to help students get a firm grasp on NLP techniques and the principles of BERT. The course syllabus includes an introduction to NLP with BERT, a sequence to sequence model, introduction to transformers in NLP, introduction to BERT, a use case of text summarization using PyTorch, and a use case of text summarization using BERT.

The course begins with an introduction to NLP, as well as its purpose and applications. This section also covers basic concepts such as tokens, lemmas, and stemming. Next, the course goes on to cover sequence to sequence models, including their purpose and basic components. It also covers the various types of neural networks used in sequence to sequence models.

The third section of the course introduces students to transformers in NLP and the different types of transformers. It also covers the purpose and principles of BERT and how it can be used in NLP tasks. The fourth section of the course focuses on a use case of text summarization using PyTorch. This section explains the process of text summarization and provides a hands-on example of creating a text summarization model using PyTorch.

Finally, the fifth section of the course discusses a use case of text summarization using BERT. This section covers the benefits of using BERT for text summarization, as well as how to create a text summarization model using BERT. It also provides a hands-on example of creating a text summarization model using BERT. After completing the course, students will have a better understanding of NLP, sequence to sequence models, transformers, and BERT, as well as how to use them for text summarization.