Skip to Content
View all events

NLP with PyTorch

Published by Pearson

Intermediate content levelIntermediate

Implement Text Classification, Sequence to Sequence Models & Word Embedding

  • Learn how to apply Pytorch for NLP tasks.
  • Use Feed-Forward Networks for Text Classification.
  • Leverage Word Embeddings for Transfer learning.
  • Apply Recurrent Neural Networks for sequence modeling.

In this course, participants are introduced to the fundamental concepts and algorithms used for Natural Language Processing (NLP) through an in-depth exploration of different examples built using the PyTorch framework for deep learning. Applications to real datasets will be explored in detail.

Natural Language lies at the heart of current developments in Artificial Intelligence, User Interaction, and Information Processing. The combination of unprecedented corpora of written text provided by social media and the massification of computational power has led to increased interest in the development of modern NLP tools based on state-of-the-art Deep Learning tools.

What you’ll learn and how you can apply it

  • Text Representation and Word Embeddings - Choose the best way to encode your text for your specific application
  • Sentiment Analysis and Text Classification - Determine what is the main sentiment or main topics covered in a text
  • Deep Learning Networks - Use Deep Learning architectures to leverage context into account when processing textual information
  • Text Generation - Produce text using Recurrent Neural Networks

This live event is for you because...

  • You need to learn how to process text data.
  • You want to understand how PyTorch can be used for NLP.
  • You want to apply deep learning approaches to text processing, understanding, and generation.

Prerequisites

  • Python
  • Basic Neural Networks

Course Set-up

  • Make sure to have Python, Jupyter notebooks and PyTorch installed on your machine. We recommend using the Anaconda distribution as it conveniently bundles Python with Jupyter notebooks and other data science tools. Finally, clone the repository at https://github.com/DataForScience/NLP_LL

Recommended Preparation

Recommended Follow-up

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Segment 1: Foundations of NLP (45 minutes)

  • One-Hot Encoding
  • TF/IDF and Stemming
  • Stopwords
  • N-grams
  • Working with Word Embeddings- Break (10 minutes)

Segment 2: Neural Networks with PyTorch (55 minutes)

  • PyTorch review
  • Activation Functions
  • Loss Functions
  • Training procedures
  • Network Architectures
  • Q&A (10 minutes)
  • Break (10 minutes)

Segment 3: Text Classification (30 minutes)

  • Feed Forward Networks
  • Convolutional Neural Networks
  • Applications

Segment 4: Word Embeddings (30 minutes)

  • Motivations
  • Skip-gram and Continuous Bag of words
  • Transfer Learning
  • Q&A (5 minutes)
  • Break (5 minutes)

Segment 5: Sequence Modeling (35 minutes)

  • Recurrent Network Networks
  • Gated Recurrent Unit
  • Long-Short Term Memory
  • Encoder-Decoder Models
  • Text Generation
  • Wrap Up (5 minutes)

Your Instructor

  • Bruno Gonçalves

    Bruno Gonçalves is an author, public speaker, corporate trainer, and consultant specializing in Generative AI, Blockchain Analytics, and Machine Learning. He has a diverse background that spans academia and industry, having previously served as a Data Science fellow at NYU's Center for Data Science while on leave from his tenured faculty position at Aix-Marseille Université. Bruno earned his PhD in the Physics of Complex Systems in 2008. He later focused his research on applying Data Science and Machine Learning to the large-scale analysis of online human behavior.

    linkedinXlinksearch

Skill covered

PyTorch