This project attempts to reproduce the results in the paper: Generating News Headlines with Recurrent Neural Networks
- The code is running with jupyter notebook
- Install Keras
pip install python-Levenshtein
It is assumed that you already have training and test data.
The data is made from many examples (I'm using 684K examples),
each example is made from the text
from the start of the article, which I call description (or desc),
and the text of the original headline (or head).
The texts should be already tokenized and the tokens separated by spaces.
Once you have the data ready save it in a python pickle file as a tuple:
(heads, descs, keywords) were heads is a list of all the head strings,
descs is a list of all the article strings in the same order and length as heads.
I ignore the keywrods information so you can place None.
The vocabulary-embedding notebook describes how a dictionary is built for the tokens and how an initial embedding matrix is built from GloVe
train notebook describes how a model is trained on the data using Keras
predict 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.
Good (cherry picking) examples of headlines generated
