FR
Clean, clear and helpful. Thanks a lot!Would also be nice to see the approaches to tune BERT for the particular task (e.g. custom tokenization, pre-processing of data, etc.)

In this 2-hour long project, you will learn how to analyze a dataset for sentiment analysis. You will learn how to read in a PyTorch BERT model, and adjust the architecture for multi-class classification. You will learn how to adjust an optimizer and scheduler for ideal training and performance. In fine-tuning this model, you will learn how to design a train and evaluate loop to monitor model performance as it trains, including saving and loading models. Finally, you will build a Sentiment Analysis model that leverages BERT's large-scale language knowledge. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

FR
Clean, clear and helpful. Thanks a lot!Would also be nice to see the approaches to tune BERT for the particular task (e.g. custom tokenization, pre-processing of data, etc.)
RA
I like this project and help me a lot to understand how to do Sentiment Analysis with BERT Model
PP
Step by Step explanation of How to practically execute the BERT Reinforced Learning
JK
There is more to learn in this. But the basics are covered well with the practical example.
SS
It was good learning experience... Thanks to coursera :)
NC
I didn't like the platform you use. Rhyme, it's not a good tool.
SN
Thanks, Ari Anastassiou for the wonderful tutorial. Hoping you do a complete course on NLP using BERT soon.
SW
The instructor explains very well on how to using bert to train a sentiment classifier. Very cool project.
WM
Good instructor, however anyone join this must have at least a knowledge in basic Python Programming and have learned about BERT and fundamental of Natural Language Processing
KA
Very good. Only if it included Inference, then it would have been perfect
SV
Thankyou, really a great course under great instructor.
RK
Required detail explanation and faculy support for error soliving and explroing alternative