Generating News Headlines with Recurrent Neural Networks
Computation and Language
2015-12-08 v1 Machine Learning
Neural and Evolutionary Computing
Abstract
We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news articles. Furthermore, we study how the neural network decides which input words to pay attention to, and specifically we identify the function of the different neurons in a simplified attention mechanism. Interestingly, our simplified attention mechanism performs better that the more complex attention mechanism on a held out set of articles.
Cite
@article{arxiv.1512.01712,
title = {Generating News Headlines with Recurrent Neural Networks},
author = {Konstantin Lopyrev},
journal= {arXiv preprint arXiv:1512.01712},
year = {2015}
}