Applied NLP

Overview

Learn how to apply statistical learning and language processing techniques to build machine learning models capable of deriving actionable insights from human language and thus enabling automated and contextual interactions between computers and humans.

Course Details

This course provides a hands-on and in-depth exploration of the industry-standard Python NLTK natural language toolkit, in combination with the Python Scikit-Learn machine learning library, with which to build natural language processing pipelines and machine learning models designed to analyze and derive meaning from text. This course explores in both theoretical and applied detail the major techniques used in natural language processing including text pre-processing, indexing, searching, categorisation, tagging, clustering, entity recognition, entity relationship recognition, word embeddings, feature detectors and custom grammars. Using these techniques, experienced senior data scientists can build digital systems capable of deriving actionable insights from human language with subsequent applications including automating contextual interactions between computers and humans via chatbots and question-answering systems.

Course Modules

• 1. Introduction to NLP
• 2. Pre-Processing Text
• 3. Indexing and Searching Text
• 4. Categorising and Tagging Text
• 5. Classifying and Clustering Text
• 6. Named Entity Recognition
• 7. Identifying Entity Relationships
• 8. Word Embeddings
• 9. Identifying Sentence Structure
• 10. Feature Detection and Grammars
• 11. Understanding Sentence Meaning
• 12. Question Answering System

Requirements

• Introduction to Python or equivalent.
• Linear Algebra or equivalent.
• Statistical Learning or equivalent.
• Applied Machine Learning or equivalent.

Outcomes

• The ability to apply statistical learning techniques to natural language processing.
• The ability to build, interpret, visualise and evaluate supervised and unsupervised machine learning models applied to real-world natural language processing use-cases including automated and contextual computer and human interaction.
• The ability to build end-to-end pipelines capable of pre-processing, modelling and learning from text.
• Advanced knowledge of the industry-standard Python NLTK natural language toolkit.