[PyTorch] Learn NLP easily and quickly

We will explain the basics of natural language processing step by step.

I organized the lectures given at Inflearn and published a book titled 'Python Deep Learning PyTorch'.

Thank you for your interest : )

(Inflearn lectures have been updated as of 2020.10.06. We will continue to update the lectures.)

http://m.yes24.com/Goods/Detail/93376077?ozsrank=10

http://mbook.interpark.com/shop/product/detail?prdNo=339742291&is1=book&is2=product

👨‍🎓 Lecture Introduction

[PyTorch] I learned the basics of deep learning through the easy and fast deep learning course.
In this lecture, you will learn the basic knowledge required for natural language processing in a relatively small amount, and learn techniques for analyzing natural language data using deep learning technology.

If you are interested in natural language processing, you may have heard of Transformer and BERT models.
However, I expect that you may not easily understand the working principles of Transformer and BERT models.
This is because of the lack of basic knowledge about natural language processing .

Therefore, in this lecture, we will learn the contents that can build basic knowledge about natural language processing .

📜 Lecture Structure

🎞 Embedding

We present limitations of the existing methodology that expressed natural language as categorical variables.
We describe a natural language expression methodology that can overcome this.
We will cover the core contents of the methodology and explain through practice how it can be used in practice .

🌀 Recurrent Neural Network

Learn about the Recurrent Neural Network (RNN) deep learning model, which can well reflect the characteristics of natural language.

We will learn the feeding process of the RNN model mathematically, and also explain the feeding process of the advanced Long Term Short Memory (LSTM) and Gated Recurrent Unit (GRU) models mathematically.

🔍 Task

There are many tasks in the field of natural language processing.
Among them, we will learn what tasks are most representative: Tagging and Neural Machine Translation .

We present a representative deep learning model structure for analysis methods along with specific examples for each task.
Describes the Weight Feeding process of data.

🎤 Attention

The limitations of the RNN model are presented, and a methodology for improving them is presented.
We introduce Attention, a recently emerging mechanism in the field of natural language processing .

Neural Machine Translation using Attention Mechanism,
We will explain how each tagging method using the Attention Mechanism can be applied.

🗓 Trend

From the perspective of a knowledge sharer, I will introduce the major areas of research currently being conducted in the field of natural language processing .
After taking this course, I will suggest a direction for how to study natural language processing.

👨‍👩‍👧‍👦 Lecture audience

• Anyone interested in natural language processing and has basic knowledge of deep learning
• Anyone familiar with the Python programming language

🙋🏼‍♀️ Expected questions related to the lecture

Q. Can you explain Transformer and BERT models in this lecture?
→ This lecture is a basic lecture on natural language processing. The goal of this lecture is to prepare the basic knowledge required when studying Transformer and BERT models. Therefore, we will briefly introduce Transformer and BERT models, but will not cover specific content.

Q. How much knowledge do I need before taking the course?
→ [PyTorch] I recommend taking the easy and fast deep learning course. In addition, if you have basic knowledge of deep learning algorithms, you can take the course sufficiently.

Q. How are the practical classes conducted?
→ I will prepare and lecture on practical code related to the theoretical content. I recommend that you share the code, but review it by writing the code line by line. (Practical code: [ https://github.com/Justin-A/ ]( https://github.com/Justin-A/torch_nlp_basic)torch_nlp_basic )

✔️ Reference lecture

[PyTorch] Learn Deep Learning Quickly and Easily
Quickly learn the concepts and related knowledge of deep learning.

👨‍💻 Introducing the knowledge sharer

Justin

• Master's Program in Industrial Engineering, Yonsei University
• Research in progress on Data Science and Deep Learning