Deep learning for natural language processing
Deep Learning for Natural Language Processing
This workshop introduces natural language as data for deep learning. We discuss various techniques and software packages (e.g. python strings, RegEx, Word2Vec) that help us convert, clean, and formalise text data “in the wild” for use in a deep learning model. We then explore the training and testing of a Recurrent Neural Network on the data to complete a real world task. We’ll be using TensorFlow v2 for this purpose.
With a balanced mix of lectures and hands-on coding, by the end of this workshop, you should be confident with the basic end-to-end process of applying deep learning techniques to natural language. We will show you how to see text as data, and how to process text depending on your intended solution. You would also be familiar with a variety of neural network architectures that are suited for natural language and time series data in general.
Difficulty level: Foundational.
Prerequisites: You should have some experience coding in Python. Additionally, it would be beneficial to have prior understanding of basic deep learning concepts such as backpropagation and gradient descent.
What you’ll need: A computer with speakers and a microphone (note: webcams and dual monitors are recommended but not required). A web browser and Zoom are the only required software. A Zoom link and instructions will be sent to registrants 2 days prior to the workshop.
How to register?
1. Monash staff and Graduate Research students register here.
Note: that Data Fluency workshops are now only available to staff and Graduate Research students.
2. External participants from Monash affiliate partners only (The Hudson Institute, The Alfred Hospital, Alfred Research Alliance Members, Peninsula Health, Baker Institute, Burnet Institute, MASSIVE and CSIRO) register here.