Another Course Completed
I have just completed the course ‘Learn BERT – the most powerful NLP algorithm by Google’. It is an advanced course that introduces…

I have just completed the course ‘Learn BERT – the most powerful NLP algorithm by Google’. It is an advanced course that introduces the use of the BERT model both theoretically and practically. Bertík is a cutting-edge algorithm from Google that, at the end of 2018, made waves in the world of natural language processing, and unfortunately, it is still used very little in practice. You will learn why it has changed the world of NLP more than any other algorithm, how to preprocess and tokenize data using BERT, how to use a pretrained model and then fine-tune it for your specific task, and much more. All of this is done in the modern environments of Google Colab and Tensorflow 2.0!
Personally, I particularly enjoyed the theoretical part of the course. The practical section lacked any examples, for instance, on Language Generation. The two examples provided—1. Multiple Choice and 2. SQuAD—barely scratch the surface of the model's capabilities. Even so, I am grateful for this first-ever online course of its kind and look forward to more.
Původní zdroj: wordpress
Související články
November 2018
This Week, Google Unveiled Its Latest Technological Toy – Bidirectional Encoder Representations Transformers, or BERT
ReadAugust 2018
A Message for AI Developers: Recently, I needed to update some libraries in Python, and in the process, TensorFlow stopped working through the GPU.
ReadJune 2018