Types of Natural Language Processing

Hadelin de Ponteves
A free video tutorial from Hadelin de Ponteves
AI Entrepreneur
4.5 instructor rating • 29 courses • 1,339,767 students

Learn more from the full course

Deep Learning and NLP A-Z™: How to create a ChatBot

Learn the Theory and How to implement state of the art Deep Natural Language Processing models in Tensorflow and Python

11:38:44 of on-demand video • Updated July 2021

  • Why this is important
  • Types of Natural Language Processing
  • Classical vs. Deep Learning Models
  • End to End Deep Learning Models
  • Seq2Seq Architecture & Training
  • Beam Search Decoding
English [Auto] Hello and welcome back to the course on deep natural language processing, and today we're going to talk about the types of natural language processing. So we've got to then diagrams here or we got a pen diagram of two circles in it. And we are going to look at the different areas of natural language processing that are going to come up in this course. So on the left, we've got natural language processing overall, and this refers to the whole circle on the left. So the reason why we've called in just this green part is because that's the non overlapping part. So we know that anything in here is just natural language processing. We followed with disregard to this second circle, but natural language processing is indeed everything that is in this first circle. Then we've got on the right deep learning. So these are all algorithms that have something to do with neural networks, deep learning. Basically anything that's called a deep learning algorithm falls in here. They don't have to be natural language processing. They can be classification. They can be anything. So they can be that's here. And natural language processing is any algorithm, any model that has something to do with processing of natural language into machine terms. And then finally, in the overlap, we have deep MLP. So these are models which have to do with natural language processing, but also which are deep learning models, which are neural network models. And so that's the part that we're going to be aiming for. But it's also very good to have visibility of all three, because in this course we will be talking about some models that fold just in here and then we'll be talking about models here. And it'll be good to compare and see how the world has changed over time and why these models are often better than these models. And the other thing to note here is that the size of these diagrams is not reflective of the importance or the volumes of these different fields. So I just said circles are the same size simply because we want a visual representation of the overlap and that these fields exist. But don't take this size into account. It's not to scale at all. And finally, there is another part, another part of this Venn diagram, which is very important to us. And it is this part over here, a sub section of a deep MLP called a sequence to sequence. So sequence to sequence models are the most cutting edge, the most powerful models that exist right now for natural language processing. And that's what we're going to be looking at. So as you'll see throughout this course, we will make our way through the natural language processing side of things into deep and l.P, and then we will go into sequence to sequence. It'll be a fun and exciting journey. And the other thing that I wanted to mention is you will also notice that throughout this course, even though it's focused on Chadbourne, so we won't be talking about just Shadowbox. We'll be looking at different examples of how these models from here and from here and from here can be applied to different things because the applications are huge. We can we can apply them in natural neural machine translation. We can apply them in image captioning, we can apply them in speech recognition, questions and answers, text summarization, lots and lots of models. So we will be looking at different ones and they will be of different types. So this map will come in handy as we go through the course and it will be popping up here and there. So I think it was very important for us to set the foundation right so that now we're ready to proceed. And I can't wait to see you on the next tutorial and until then, enjoy deep and natural language processing.