Generative Adversarial Network for Abstractive Text Summarization

26 Nov 2017  ·  Linqing Liu, Yao Lu, Min Yang, Qiang Qu, Jia Zhu, Hongyan Li ·

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.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Summarization CNN / Daily Mail (Anonymized) GAN ROUGE-1 39.92 # 5
ROUGE-2 17.65 # 4
ROUGE-L 36.71 # 7


No methods listed for this paper. Add relevant methods here