In Module 2, you'll dive into the world of named entity recognition (NER). You'll learn to define and identify named entities, and understand how to tackle related tasks by framing them as NER challenges. We'll explore how to use resources like standardized terminology and named gazettes to enhance NER. You'll also gain hands-on experience by training a machine learning model for sequence classification using an annotated text dataset. Finally, we'll discuss the pros and cons of different Markov models for NER, equipping you with the insights needed for practical applications.

In Module 3, focused on neural network models, you will explore the differences between training deep learning models and traditional machine learning models. You'll learn how to model and train a neural network-based classifier, as well as formulate text as features for NER model training. We will discuss the pros and cons of deep learning approaches. You'll design a neural network model to identify concepts from free text and apply a trained deep learning model to solve NER tasks.

In this module, you'll dive into the power of deep learning models in diverse fields such as healthcare and sports commentary. You'll learn how to build neural network models that are fine-tuned for specific tasks and discover how to set up a deep neural network for detecting key entities. We'll also introduce you to the world of large language models, showcasing their transformative capabilities and applications in information extraction.