A Beginner's Guide to Deep Natural Language Processing with PyTorch

Are you a newbie in NLP? Have you recently been intrigued by the hype of deep learning? Do you want to get your hands dirty? This talk is for you! I will teach you the basic ideas of NLP, basic building blocks of deep learning, and how to assemble them into a piece of workable code in Python.

Natural Language Processing (NLP) is a challenging subfield of Artificial Intelligence, in which human’s ability to understand and produce language is imitated. With the advent of deep learning in mid-2000s, many NLP tasks previously done in traditional statistical methods have gained significant accuracy improvement, thanks to its powerful feature extraction.

This talk will dive into the basic ideas of natural language processing, some building blocks of neural networks for deep learning, and how to assemble them into a piece of runnable code for various NLP tasks. PyTorch will be used as the main gear, because we can easily cope with both static and dynamic network architectures while maintaining the code readability. The speaker kindly assumes the audience to have some knowledge in Python (intermediate: especially classes and objects), university calculus (basic), and linguistics (very basic).

The talk will be (preferably) conducted in English. The Q/A session can be done in both English and Thai.

Technical requirements for the audience

• Python: intermediate (especially classes and objects)

• University calculus: basic

• Linguistics: very basic

The speaker is a computational linguist and a computer scientist with 16-years experience in natural language processing (NLP) using Python. He has been using both statistical methods and deep learning methods in his research, and he also has some teaching experiences in the area of NLP.