Generative Adversarial Network for Abstractive Text Summarization

Authors

  • Linqing Liu Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Yao Lu Alberta Machine Intelligence Institute
  • Min Yang Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Qiang Qu Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Jia Zhu South China Normal University
  • Hongyan Li Peking University

Keywords:

abstractive text summarization

Abstract

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization. We also build a discriminator which attempts to distinguish the generated summary from the ground truth summary. Extensive experiments demonstrate that our model achieves competitive ROUGE scores with the state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show that our model is able to generate more abstractive, readable and diverse summaries.

Downloads

Published

2018-04-29

How to Cite

Liu, L., Lu, Y., Yang, M., Qu, Q., Zhu, J., & Li, H. (2018). Generative Adversarial Network for Abstractive Text Summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12141