Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.
@article{arxiv.1509.00685,
title = {A Neural Attention Model for Abstractive Sentence Summarization},
author = {Alexander M. Rush and Sumit Chopra and Jason Weston},
journal= {arXiv preprint arXiv:1509.00685},
year = {2015}
}