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.

Improving your movie review classifier

Improving your movie review classifier - TensorFlow Tutorial

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

Start my 1-month free trial

Improving your movie review classifier

- So far, we have seen how the LSTM Layer or the LSTM Model has performed, in classifying text or classifying headlines as sarcastic and non-sarcastic. We've witnessed a bit of all fitting with the LSTM model. In this video we are going to try to improve the performance of the model using a Convolution Layer. So we've been using Convolution for image classification but we'll see how we can use the Convolution Layer for text classification purposes. Users using the same code, same packages. So using the same dataset as well, everything remains the same, embedding dimension, all of the parameters, sequences, number by areas. So let's get down to model definition. So here, we have a sequential model. So first of all, the first layer would remain the same, embedding layer, where the vocabulary size equals 100 embedding dimension and set 264 and input length max length that is also defined to be a hundred. Now we add a…

Contents