Overview

In “Applied Information Extraction in Python,” you will learn how to extract useful information from free-text data, which is a type of string data created when people type. Examples of free-text data include names of people or organizations, location information such as cities and zip codes, or other elements like stock prices or clinical diagnoses. Free-text data is found everywhere, from magazine articles to social media posts, and can be complex to analyze. In this course, you’ll use applied machine learning and text-mining techniques to analyze free-text data. You will learn how to identify named entities and tag them with appropriate types of classifications, using real-world data from business, politics, and healthcare. You’ll develop multiple approaches to recognize and extract named entities and attributes of interest from free-text data, ranging from regular expressions to neural network models. Finally, you’ll explore Transformer models such as ChatGPT and Large Language Models to extract information from large datasets. This is the final course in “More Applied Data Science with Python,” a four-course series focused on helping you apply advanced data science techniques using Python. It is recommended that all learners complete the following courses from the Applied Data Science with Python Specialization: Introduction to Data Science in Python, Applied Machine Learning in Python, and Applied Text Mining in Python.

Syllabus

Information Extraction

This module introduces information extraction, covering key tasks and approaches for extracting relevant information from text. You will explore pattern-based and list-based methods to identify and extract information from text data, applying these techniques across diverse domains. You will also develop an end-to-end NLP pipeline to extract named entities from free text using terminology resources.

Named Entity Recognition (NER)

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.

Neural Network Models

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.

Transformers Transform Information Extraction

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.