What you will learn
You will learn all the fundamental skills you need to extract syntactic, semantic and even emotional information from text.
- Text processing (parsing, tokenisation, lematisation)
- Syntactic analysis (POS tagging)
- Semantic analysis (word vector analysis, IR techniques)
- Topic analysis
- Language models and text generation
Languages and libraries
- Python programming language
- numpy and pandas for data manipulation
- scikit-learn for machine learning algorithms
- plotly for interactive visualisations
How you will learn
The course is extremely interactive and hands-on. You will learn by working through concrete problems with real datasets. You will be taught by specialists in the field, who have a wealth of experience and knowledge to share.
Is it for me?
Audience: Those wishing to understand how to implement the intelligent text processing behind many of the latest technologies and applications, such as content labelling, content recommendation and predictive texting.
Level: Intermediate (ideally you will have attended the Introduction to Data Science bootcamp)
Prerequisites: good knowledge of python, some familiarity with matrices, basic understanding of machine learning practice (as taught in Introduction to Data Science)
For further information about this two-day Bootcamp visit: http://cambridgecoding.com/workshop/nlp