Text Classification Using Word2Vec and LSTM on Keras

4.3
stars
6 ratings
Offered By
Coursera Project Network
In this Guided Project, you will:

Learn how to create a Text Classifier using Word Embeddings and LSTM on Tensorflow & Keras.

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2-hour long project-based course, you will learn how to do text classification use pre-trained Word Embeddings and Long Short Term Memory (LSTM) Neural Network using the Deep Learning Framework of Keras and Tensorflow in Python. We will be using Google Colab for writing our code and training the model using the GPU runtime provided by Google on the Notebook. We will first train a Word2Vec model and use its output in the embedding layer of our Deep Learning model LSTM which will then be evaluated for its accuracy and loss on unknown data and tested on few samples. 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.

Skills you will develop

Deep LearningWord2vecPython ProgrammingLong Short-Term Memory (ISTM)keras

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Introduction & Setting up Google Colab

  2. Loading the Dataset

  3. Preprocessing the Data for Word2Vec

  4. Training the Word2Vec model

  5. Testing the Word2Vec Model

  6. Preparing data for LSTM

  7. Training the LSTM model

  8. Evaluating the LSTM model

  9. Plotting the model performance metrics

  10. Testing the model performance

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.