Need help with How_to_make_a_text_summarizer?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

465 Stars 307 Forks MIT License 10 Commits 18 Opened issues


This is the code for "How to Make a Text Summarizer - Intro to Deep Learning #10" by Siraj Raval on Youtube

Services available


Need anything else?

Contributors list

# 12,130
6 commits
# 20,887
3 commits


This is the code for "How to Make a Text Summarizer - Intro to Deep Learning #10" by Siraj Raval on Youtube.

Coding Challenge - Due Date - Thursday, March 23rd at 12 PM PST

The challenge for this video is to make a text summarizer for a set of articles with Keras. You can use any textual dataset to do this. By doing this you'll learn more about encoder-decoder architecture and the role of attention in deep learning. Good luck!


This is the code for this video on Youtube by Siraj Raval as part of the Deep Learning Nanodegree with Udacity. We're using an encoder-decoder architecture to generate a headline from a news article.


  • Tensorflow or Theano
  • Keras
  • python-Levenshtein (pip install python-levenshtein)

Use pip to install any missing dependencies.

Basic Usage


The video example is made from the text at the start of the article, which I call description (or

), and the text of the original headline (or
). The texts should be already tokenized and the tokens separated by spaces. This is a good example dataset. You can use the 'content' as the 'desc' and the 'title' as the 'head'.

Once you have the data ready save it in a python pickle file as a tuple:

(heads, descs, keywords)
is a list of all the head strings,
is a list of all the article strings in the same order and length as
. I ignore the
information so you can place

Here is a link on how to get similar datasets

Build a vocabulary of words

The vocabulary-embedding notebook describes how a dictionary is built for the tokens and how an initial embedding matrix is built from GloVe.

Train a model

The train notebook describes how a model is trained on the data using Keras.

Use model to generate new headlines

The predict notebook generate headlines by the trained model and showes the attention weights used to pick words from the description. The text generation includes a feature which was not described in the original paper, it allows for words that are outside the training vocabulary to be copied from the description to the generated headline.

Examples of headlines generated

Good (cherry-picked) examples of headlines generated: cherry picking of generated headlines cherry picking of generated headlines

Examples of attention weights

attention weights


The credit for this code goes to udibr i've merely created a wrapper to make it easier to get started.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.