From the course: Deep Learning with Python and Keras: Build a Model for Sentiment Analysis

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Representing text using integer sequences

Representing text using integer sequences

From the course: Deep Learning with Python and Keras: Build a Model for Sentiment Analysis

Start my 1-month free trial Buy for my team

Representing text using integer sequences

“

- [Instructor] In this demo, we'll change the way we represent our input text data that we use to train our model. Instead of using count vectors or TF-IDF vectors, we'll generate embeddings on the input text. Embeddings are dense vector representations of text that capture the semantics and relationships between words. Similar words have similar embeddings. Embeddings do not have to be manually generated. Instead, the embeddings are generated using trainable parameters the same way the model learns weights for a dense layer. We'll generate embeddings for our input text using an embedding layer in the neural network. Let's get Gemini's help to set up the text vectorization layer so that it outputs integers that can then be fed into our model that will contain an embedding layer. Observe that I ask Gemini to set up the text vectorization layer so I can work with embeddings for sentiment analysis. I don't indicate that…

Contents