Convolutions for Text Classification with Keras
Offered By: Coursera Project Network via Coursera
Course Description
Overview
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.
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.
Syllabus
- Convolutions for Text Classification with Keras
- 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.
Taught by
Snehan Kekre
Related Courses
Rethinking Security in an Era of Online Hate and HarassmentUSENIX Enigma Conference via YouTube LGBTQ - Has the Internet Helped?
Collision Conference via YouTube Uncovering Data Injustice - Global Perspectives on Technology and Social Justice
Alan Turing Institute via YouTube Formalizing User Rights on the Web
JSConf via YouTube Opt Out of Online Sexism – Open Source Activism
EuroPython Conference via YouTube