Convolutions for Text Classification with Keras

112 ratings
Offered By
Coursera Project Network
3,828 already enrolled
In this Guided Project, you will:

Apply Word Embeddings for Text Classification

Use 1D Convolutions as Feature Extractors for Text in NLP

Perform Binary Text Classification using Deep Learning with Keras

Clock1.5 hours
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

Welcome to this hands-on, guided introduction to Text Classification using 1D Convolutions with Keras. By the end of this project, you will be able to apply word embeddings for text classification, use 1D convolutions as feature extractors in natural language processing (NLP), and perform binary text classification using deep learning. As a case study, we will work on classifying a large number of Wikipedia comments as being either toxic or not (i.e. comments that are rude, disrespectful, or otherwise likely to make someone leave a discussion). This issue is especially important, given the conversations the global community and tech companies are having on content moderation, online harassment, and inclusivity. The data set we will use comes from the Toxic Comment Classification Challenge on Kaggle. To complete this guided project, we recommend that you have prior experience in Python programming, deep learning theory, and have used either Tensorflow or Keras to build deep learning models. We assume you have this foundational knowledge and want to learn how to use convolutions in NLP tasks such as classification. Note: This course works best for learners based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop


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 and Import Packages

  2. Load and Explore the Data

  3. Data Preparation — Tokenize and Pad Text Data

  4. Prepare Embedding Matrix with Pre-trained GloVe Embeddings

  5. Create the Embedding Layer

  6. Build the Model

  7. Train the Model

  8. Model Evaluation - Classify Toxic Comments

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



View all reviews

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.