The majority of data is unstructured. This includes information recorded in books, online articles, and audio files. In this track, you’ll gain the core Natural Language Processing (NLP) skills you need to convert that data into valuable insights—from learning how to automatically transcribe TED talks through to identifying whether a movie review is positive or negative. Along the way, you’ll be introduced to popular NLP Python libraries, including NLTK, scikit-learn, spaCy, and SpeechRecognition. By the end of the track, you'll be ready to transcribe audio files and understand how to extract insights from real-world sources, including Wikipedia articles, online review sites, and data from a flight booking system.
Overview
Syllabus
- Natural Language Processing (NLP) in Python
- Master text analysis with essential NLP techniques from preprocessing to advanced transformer models.
- Sentiment Analysis in Python
- Are customers thrilled with your products or is your service lacking? Learn how to perform an end-to-end sentiment analysis task.
- Natural Language Processing with spaCy
- Master the core operations of spaCy and train models for natural language processing. Extract information from unstructured data and match patterns.
- Spoken Language Processing in Python
- Learn how to load, transform, and transcribe speech from raw audio files in Python.
- Analyzing Customer Support Calls
- Feature Engineering for NLP in Python
- Learn techniques to extract useful information from text and process them into a format suitable for machine learning.
Taught by
Katharine Jarmul, Rounak Banik, Violeta Misheva, Daniel Bourke, and Azadeh Mobasher