From the course: Deep Learning Foundations: Natural Language Processing with TensorFlow

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Challenge: Yelp review classifier

Challenge: Yelp review classifier - TensorFlow Tutorial

From the course: Deep Learning Foundations: Natural Language Processing with TensorFlow

Start my 1-month free trial

Challenge: Yelp review classifier

(upbeat techno music) - [Instructor] So you've seen how an LSTM layer or a convolutional layer can be added to the model to classify text. Now, in this particular challenge, I want you to implement and explore LSTM and convolution model over this new Yelp review dataset from TensorFlow dataset package. Now, I have already provided the code snippet to download the Yelp popularity reviews. So accordingly, you will have both your training testing as well with the IMDb dataset from the TFDS package. So you have to fill up all of these blanks: vocabulary size, embedding dimension. Feel free to tweak your parameters, manipulate those numbers. And try a combination of them, different combinations. And then you have to define the model first. Try to work with an LSTM model and then do a CNN. So fill up all of these blanks and see how you get to classify those texts. And what sort of accuracy and loss you witness with the new…

Contents