Generative Adversarial Network for Abstractive Text Summarization

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 summaries1.

Authors

• Linqing Liu
• Yao Lu Harbin Institute of Technology, Shenzhen
• Min Yang Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences, Shenzhen, China
• Qiang Qu Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
• Jia Zhu Zhejiang Normal University
• Hongyan Li Peking University

Keywords

No keywords are indexed for this paper.