Apply Deep Learning to Natural Language Processing (NLP)
Deep Learning is a powerful technique that has revolutionized many industries by dealing with unstructured data in a novel and different way. Textual data is one of these. Discover current state-of-the-art techniques that can help — for example — to determine intent and sentiment in text. This 2-day training offers a deep-dive into game-changer tech!
This Deep Learning Applied to NLP training is perfect for Data Scientists who
- Know Machine Learning and Deep Learning and would like to apply it to textual data;
- Want to go beyond the standard NLP techniques;
- Have at least one year of working experience with pandas and scikit-Learn.
What will you learn during the Deep Learning Applied to NLP
- This course helps you understand what makes Deep Learning so powerful, especially compared to the traditional techniques, when applied to NLP
- You will understand and be able to use Bert models
- We will also teach you how about embeddings, dimensionality reduction, and how to build these using the Keras API.
Deep Learning Applied to NLP – Program
The program of this two-day Deep Learning Applied to NLP course is as follows:
Day 1: Theory and Labs
- 1. Introduction
2. Baseline NLP models
3. Building deep NLP models
4. The encoder-decoder architecture
5. Attention mechanism (BERT)
6. Transfer learning in NLP (Hugging face)
Day 2: Hackathon
Benchmark the performance of bag of word models vs. deep learning models on short texts. The participants need to write benchmarking scripts that compare a scikit-learn pipeline against a deep learning model written in Keras. The scikit-learn pipeline will also require the students writing a transformer that accepts Bert/Spacy embeddings to see the benefits of using pretrained models.
During this training, you will go in-depth with Bayesian Probability. After this training, you are knowledgeable about the following topics.
You will learn:
- The theory that underlies Deep Learning and learn to apply it to solve Natural Language Processing problems.
- How Deep Learning can be applied to textual data and make yourself comfortable with the Natural Language Processing terminology: embeddings, dimensionality reduction, and more.
- How the Deep Learning approach is fundamentally different than the traditional approach;
- The (practical) pros and cons of working with either approach.
- How to apply transfer learning in NLP and use pretrained Bert models.
This training is available in the following formats:
In-Company training is perfect for groups of 6 or more. The training takes place at your office or at one of our modern training facilities.
Online Virtual Classroom
Virtual Classrooms provide you with an interactive environment to effectively develop your skills, right from the comfort of your own home or office.