Natural Language Processing is a sub-field of Artificial Intelligence. It is used for processing and analysing large amounts of natural language (linguistics). Some applications include search engines (Google), text classification (spam filters), identifying sentiments for a product (sentiment analysis), methods for discovering abstract topics in a collection of documents (topic modelling) and machine translation technologies.
Aims, Objectives and Intended Learning Outcomes
This course will provide an introduction to the Natural Language Processing field using Python programming language. It covers some basic terminology, the process of ‘cleaning’ a dataset, exploring it and applying simple feature engineering techniques to transform the data. By the end of the module learners will understand and apply the necessary steps to ‘clean’, explore and transform their dataset in order to produce data science products.
Working knowledge of python: familiarity with pandas and basic python objects such as strings and lists. This can be obtained with the Introduction to Python or equivalent course.